Search

Massive trajectory data stem from the prevalence of equipment-supporting GPS and wireless communication technology. Especially, activity trajectory from LBSN endows traditional trajectory data with additional user semantic activities. Measuring the similarity between activity trajectories is to compare their proximity in multiple dimensions such as time, location, and semantics. In this way, we can mine implicit user preference and apply it to route planning, POI recommendation or any other online tasks. The key challenge of comparing activity trajectories lies in two aspects. One is the uneven sampling rate in both time and space. The other is the discrepancy of individual activities. Previous effort alleviates the issue of uneven sampling rate via trajectory complements, which is limited to spatial-temporal information. In this paper, we propose to learn a representation for one activity trajectory by jointly considering the spatio-temporal characteristics and the activity semantics. The similarity of two trajectories is computed by weighting individual trajectory points and contextual features with multi-level attention mechanisms. In specific, we propose a point-level and feature-level attention mechanism to adaptively select critical elements and contextual factors for learning trajectory representation. Our proposed approach, called At2vec, demonstrates better performance than existing baselines in extensive experimental evaluation on real databases.

Multi-label active learning (MAL) aims to learn an accurate multi-label classifier by selecting which examples (or example-label pairs) will be annotated and reducing query effort. MAL is more complicated, since one example can be associated with a set of non-exclusive labels and the annotator has to scrutinize the whole example and label space to provide correct annotations. Instead of scrutinizing the whole example for annotation, we may just examine some of its subexamples with respect to a label for annotation. In this way, we can not only save the annotation cost but also speedup the annotation process. Given that, we a two-stage Cost-effective MAL strategy (CMAL) by querying subexamples. CMAL firstly selects the most informative example-label pairs by leveraging uncertainty, label correlation and label space sparsity. Next, CMAL greedily queries the most probable positive subexample-label pairs of the selected example-label pairs. In addition, we propose rCMAL to account for the representative of examples to more reliably select example-label pairs. Extensive experiments on multi-label datasets show that our proposed CMAL and rCMAL can better save the query cost than state-of-the-art MAL methods. The contribution of leveraging label correlation, label sparsity and representative for saving cost is also confirm.

In multiview multilabel learning, each object is represented by several heterogeneous feature representations and is also annotated with a set of discrete nonexclusive labels. Previous studies typically focus on capturing the shared latent patterns among multiple views, while not sufficiently considering the diverse characteristics of individual views, which can cause performance degradation. In this article, we propose a novel approach [individuality- and commonality-based multiview multilabel learning (ICM2L)] to explicitly explore the individuality and commonality information of multilabel multiple view data in a unified model. Specifically, a common subspace is learned across different views to capture the shared patterns. Then, multiple individual classifiers are exploited to explore the characteristics of individual views. Next, an ensemble strategy is adopted to make a prediction. Finally, we develop an alternative solution to jointly optimize our model, which can enhance the robustness of the proposed model toward rare labels and reinforce the reciprocal effects of individuality and commonality among heterogeneous views, and thus further improve the performance. Experiments on various real-word datasets validate the effectiveness of ICM2L against the state-of-the-art solutions, and ICM2L can leverage the individuality and commonality information to achieve an improved performance as well as to enhance the robustness toward rare labels.

In this paper, we explore the multi-classification problem of acupuncture acupoints based on Bert model, i.e., we try to recommend the best main acupuncture point for treating the disease by classifying and predicting the main acupuncture point for the disease, and further explore its acupuncture point grouping to provide the medical practitioner with the optimal solution for treating the disease and improving the clinical decision-making ability. The Bert-Chinese-Acupoint model was constructed by retraining on the basis of the Bert model, and the semantic features in terms of acupuncture points were added to the acupuncture point corpus in the fine-tuning process to increase the semantic features in terms of acupuncture points, and compared with the machine learning method. The results show that the Bert-Chinese Acupoint model proposed in this paper has a 3% improvement in accuracy compared to the best performing model in the machine learning approach.

Crowdsourcing is a relatively inexpensive and efficient mechanism to collect annotations of data from the open Internet. Crowdsourcing workers are paid for the provided annotations, but the task requester usually has a limited budget. It is desirable to wisely assign the appropriate task to the right workers, so the overall annotation quality is maximized while the cost is reduced. In this article, we propose a novel task assignment strategy (CrowdWT) to capture the complex interactions between tasks and workers, and properly assign tasks to workers. CrowdWT first develops a Worker Bias Model (WBM) to jointly model the worker’s bias, the ground truths of tasks, and the task features. WBM constructs a mapping between task features and worker annotations to dynamically assign the task to a group of workers, who are more likely to give correct annotations for the task. CrowdWT further introduces a Task Difficulty Model (TDM), which builds a Kernel ridge regressor based on task features to quantify the intrinsic difficulty of tasks and thus to assign the difficult tasks to more reliable workers. Finally, CrowdWT combines WBM and TDM into a unified model to dynamically assign tasks to a group of workers and recall more reliable and even expert workers to annotate the difficult tasks. Our experimental results on two real-world datasets and two semi-synthetic datasets show that CrowdWT achieves high-quality answers within a limited budget, and has the best performance against competitive methods.

Heterogeneous network based data fusion can encode diverse inter- and intra-relations between objects, and has been sparking increasing attention in recent years. Matrix factorization based data fusion models have been invented to fuse multiple data sources. However, these models generally suffer from the widely-witnessed insufficient relations between nodes and from information loss when heterogeneous attributes of diverse network nodes are transformed into ad-hoc homologous networks for fusion. In this paper, we introduce a general data fusion model called Attributed Heterogeneous Network Fusion (AHNF). AHNF firstly constructs an attributed heterogeneous network composed with different types of nodes and the diverse attribute vectors of these nodes. It uses indicator matrices to differentiate the observed inter-relations from the latent ones, and thus reduces the impact of insufficient relations between nodes. Next, it collaboratively factorizes multiple adjacency matrices and attribute data matrices of the heterogeneous network into low-rank matrices to explore the latent relations between these nodes. In this way, both the network topology and diverse attributes of nodes are fused in a coordinated fashion. Finally, it uses the optimized low-rank matrices to approximate the target relational data matrix of objects and to effectively accomplish the relation prediction. We apply AHNF to predict the lncRNA-disease associations using diverse relational and attribute data sources. AHNF achieves a larger area under the receiver operating curve 0.9367 (by at least 2.14%), and a larger area under the precision-recall curve 0.5937 (by at least 28.53%) than competitive data fusion approaches. AHNF also outperforms competing methods on predicting de novo lncRNA-disease associations, and precisely identifies lncRNAs associated with breast, stomach, prostate, and pancreatic cancers. AHNF is a comprehensive data fusion framework for universal attributed multi-type relational data. The code and datasets are available at http://mlda.swu.edu.cn/codes.php?name=AHNF .

Approximate nearest neighbor (ANN) search in high-dimensional spaces is fundamental in many applications. Locality-sensitive hashing (LSH) is a well-known methodology to solve the ANN problem. Existing LSH-based ANN solutions typically employ a large number of individual indexes optimized for searching efficiency. Updating such indexes might be impractical when processing high-dimensional streaming data. In this paper, we present a novel disk-based LSH index that offers efficient support for both searches and updates. The contributions of our work are threefold. First, we use the write-friendly LSM-trees to store the LSH projections to facilitate efficient updates. Second, we develop a novel estimation scheme to estimate the number of required LSH functions, with which the disk storage and access costs are effectively reduced. Third, we exploit both the collision number and the projection distance to improve the efficiency of candidate selection, improving the search performance with theoretical guarantees on the result quality. Experiments on four real-world datasets show that our proposal outperforms the state-of-the-art schemes.

Multi-view clustering aims at integrating complementary information from multiple heterogeneous views to improve clustering results. Existing multi-view clustering solutions can only output a single clustering of the data. Due to their multiplicity, multi-view data, can have different groupings that are reasonable and interesting from different perspectives. However, how to find multiple, meaningful, and diverse clustering results from multi-view data is still a rarely studied and challenging topic in multi-view clustering and multiple clusterings. In this paper, we introduce a deep matrix factorization based solution (DMClusts) to discover multiple clusterings. DMClusts gradually factorizes multi-view data matrices into representational subspaces layer-by-layer and generates one clustering in each layer. To enforce the diversity between generated clusterings, it minimizes a new redundancy quantification term derived from the proximity between samples in these subspaces. We further introduce an iterative optimization procedure to simultaneously seek multiple clusterings with quality and diversity. Experimental results on benchmark datasets confirm that DMClusts outperforms state-of-the-art multiple clustering solutions.

For federated learning systems deployed in the wild, data flaws hosted on local agents are widely witnessed. On one hand, given a large amount (e.g. over 60%) of training data are corrupted by systematic sensor noise and environmental perturbations, the performances of federated model training can be degraded significantly. On the other hand, it is prohibitively expensive for either clients or service providers to set up manual sanitary checks to verify the quality of data instances. In our study, we echo this challenge by proposing a collaborative and privacy-preserving machine teaching method. Specifically, we use a few trusted instances provided by teachers as benign examples in the teaching process. Our collaborative teaching approach seeks jointly the optimal tuning on the distributed training set, such that the model learned from the tuned training set predicts labels of the trusted items correctly. The proposed method couples the process of teaching and learning and thus produces directly a robust prediction model despite the extremely pervasive systematic data corruption. The experimental study on real benchmark data sets demonstrates the validity of our method.

Data prediction and imputation are important parts of marine animal movement trajectory analysis as they can help researchers understand animal movement patterns and address missing data issues. Compared with traditional methods, deep learning methods can usually provide enhanced pattern extraction capabilities, but their applications in marine data analysis are still limited. In this research, we propose a composite deep learning model to improve the accuracy of marine animal trajectory prediction and imputation. The model extracts patterns from the trajectories with an encoder network and reconstructs the trajectories using these patterns with a decoder network. We use attention mechanisms to highlight certain extracted patterns as well for the decoder. We also feed these patterns into a second decoder for prediction and imputation. Therefore, our approach is a coupling of unsupervised learning with the encoder and the first decoder and supervised learning with the encoder and the second decoder. Experimental results demonstrate that our approach can reduce errors by at least 10% on average comparing with other methods.

In modern e-commerce, the temporal order behind users’ transactions implies the importance of exploiting the transition dependency among items for better inferring what a user prefers to interact in “near future”. The types of interaction among items are usually divided into individual-level interaction that can stand out the transition order between a pair of items, or union-level relation between a set of items and single one. However, most of existing work only captures one of them from a single view, especially on modeling the individual-level interaction. In this paper, we propose a Multi-order Attentive Ranking Model (MARank) to unify both individual- and union-level item interaction into preference inference model from multiple views. The idea is to represent user’s short-term preference by embedding user himself and a set of present items into multi-order features from intermedia hidden status of a deep neural network. With the help of attention mechanism, we can obtain a unified embedding to keep the individual-level interactions with a linear combination of mapped items’ features. Then, we feed the aggregated embedding to a designed residual neural network to capture union-level interaction. Thorough experiments are conducted to show the features of MARank under various component settings. Furthermore experimental results on several public datasets show that MARank significantly outperforms the state-of-the-art baselines on different evaluation metrics. The source code can be found at https://github.com/voladorlu/MARank.

Data mining has actively contributed to solving many real-world problems with a variety of techniques. Traditional approaches in this field are classification, clustering and regression. During the last few years a number of chal-lenges have emerged, such as imbalanced data, multi-label and multi-instance problems, low quality and/or noisy data or semi-supervised learning, among others [item 1) in the Appendix]. When these non-standard scenarios are encountered in the realm of big data, it remains an uncharted research territory, although a growing effort has been made to break the limits. The current trend is to address the classical and newly emerging data mining problems in big data and knowledge processing. Granular computing provides a powerful tool for multiple granularity and multiple-view data analysis at differ-ent granularity levels, which has demonstrated strong capabil-ities and advantages in intelligent data analysis, pattern recog-nition, machine learning and uncertain reasoning [item 2) inthe Appendix]. Big data often contains a significant amount of unstructured, uncertain and imprecise data. There are new challenges regarding the scalability of granular computing when addressing very big data sets [item 3) in the Appendix]. Big data mining relies on distributed computational strate-gies; it is often impossible to store and process data on one single computing node. The exploration of data mining and granular computing in big data and knowledge processing is an emerging field which crosses multiple research disciplines and industry domains, including transportation, communications, social network, medical health, and so on.

In recent years, recommender systems play a pivotal role in helping users identify the most suitable items that satisfy personal preferences. As user-item interactions can be naturally modelled as graph-structured data, variants of graph convolutional networks (GCNs) have become a well-established building block in the latest recommenders. Due to the wide utilization of sensitive user profile data, existing recommendation paradigms are likely to expose users to the threat of privacy breach, and GCN-based recommenders are no exception. Apart from the leakage of raw user data, the fragility of current recommenders under inference attacks offers malicious attackers a backdoor to estimate users' private attributes via their behavioral footprints and the recommendation results. However, little attention has been paid to developing recommender systems that can defend such attribute inference attacks, and existing works achieve attack resistance by either sacrificing considerable recommendation accuracy or only covering specific attack models or protected information. In our paper, we propose GERAI, a novel differentially private graph convolutional network to address such limitations. Specifically, in GERAI, we bind the information perturbation mechanism in differential privacy with the recommendation capability of graph convolutional networks. Furthermore, based on local differential privacy and functional mechanism, we innovatively devise a dual-stage encryption paradigm to simultaneously enforce privacy guarantee on users' sensitive features and the model optimization process. Extensive experiments show the superiority of GERAI in terms of its resistance to attribute inference attacks and recommendation effectiveness.

Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems. Most existing social recommendation models exploit pairwise relations to mine potential user preferences. However, real-life interactions among users are very complicated and user relations can be high-order. Hypergraph provides a natural way to model complex high-order relations, while its potentials for improving social recommendation are under-explored. In this paper, we fill this gap and propose a multi-channel hypergraph convolutional network to enhance social recommendation by leveraging high-order user relations. Technically, each channel in the network encodes a hypergraph that depicts a common high-order user relation pattern via hypergraph convolution. By aggregating the embeddings learned through multiple channels, we obtain comprehensive user representations to generate recommendation results. However, the aggregation operation might also obscure the inherent characteristics of different types of high-order connectivity information. To compensate for the aggregating loss, we innovatively integrate self-supervised learning into the training of the hypergraph convolutional network to regain the connectivity information with hierarchical mutual information maximization. The experimental results on multiple real-world datasets show that the proposed model outperforms the SOTA methods, and the ablation study verifies the effectiveness of the multi-channel setting and the self-supervised task. The implementation of our model is available via https://github.com/Coder-Yu/RecQ., Comment: 11 pages, Accepted by WWW'21. Correct some typos in the previous version

With the ubiquitous graph-structured data in various applications, models that can learn compact but expressive vector representations of nodes have become highly desirable. Recently, bearing the message passing paradigm, graph neural networks (GNNs) have greatly advanced the performance of node representation learning on graphs. However, a majority class of GNNs are only designed for homogeneous graphs, leading to inferior adaptivity to the more informative heterogeneous graphs with various types of nodes and edges. Also, despite the necessity of inductively producing representations for completely new nodes (e.g., in streaming scenarios), few heterogeneous GNNs can bypass the transductive learning scheme where all nodes must be known during training. Furthermore, the training efficiency of most heterogeneous GNNs has been hindered by their sophisticated designs for extracting the semantics associated with each meta path or relation. In this paper, we propose WIde and DEep message passing Network (WIDEN) to cope with the aforementioned problems about heterogeneity, inductiveness, and efficiency that are rarely investigated together in graph representation learning. In WIDEN, we propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes. To further improve the training efficiency, we innovatively present an active downsampling strategy that drops unimportant neighbor nodes to facilitate faster information propagation. Experiments on three real-world heterogeneous graphs have further validated the efficacy of WIDEN on both transductive and inductive node representation learning, as well as the superior training efficiency against state-of-the-art baselines., Manuscript is under review

Multiview multi-instance multilabel learning (M3L) is a framework for modeling black complex objects. In this framework, each object (or bag) contains one or more instances, is represented with different feature views, and simultaneously annotated with a set of nonexclusive semantic labels. Given the multiplicity of the studied objects, traditional M3L methods generally demand a large number of labeled bags to train a predictive model to annotate bags (or instances) with semantic labels. However, annotating sufficient bags is very expensive and often impractical. In this article, we present an active learning-based M3L approach (M3AL) to reduce the labeling costs of bags and to improve the performance as much as possible. M3AL first adapts the multiview self-representation learning to evacuate the shared and individual information of bags and to learn the shared/individual similarities between bags across/within views. Next, to avoid scrutinizing all the possible labels, M3AL introduces a new query strategy that leverages the shared and individual information, and the diverse instance distribution of bags across views, to select the most informative bag-label pair for the query. Experimental studies on benchmark data sets show that M3AL can significantly reduce the query costs while achieving a better performance than other related competitive methods at the same cost.

Despite of the pervasive existence of multi-label evasion attack, it is an open yet essential problem to characterize the origin of the adversarial vulnerability of a multi-label learning system and assess its attackability. In this study, we focus on non-targeted evasion attack against multi-label classifiers. The goal of the threat is to cause miss-classification with respect to as many labels as possible, with the same input perturbation. Our work gains in-depth understanding about the multi-label adversarial attack by first characterizing the transferability of the attack based on the functional properties of the multi-label classifier. We unveil how the transferability level of the attack determines the attackability of the classifier via establishing an information-theoretic analysis of the adversarial risk. Furthermore, we propose a transferability-centered attackability assessment, named Soft Attackability Estimator (SAE), to evaluate the intrinsic vulnerability level of the targeted multi-label classifier. This estimator is then integrated as a transferability-tuning regularization term into the multi-label learning paradigm to achieve adversarially robust classification. The experimental study on real-world data echos the theoretical analysis and verify the validity of the transferability-regularized multi-label learning method., Comment: Accepted in ECML-PKDD 2021

Recognizing high potential scholars has become an important problem in recent years. However, conventional scholar evaluating methods based on hand-crafted metrics can not profile the scholars in a dynamic and comprehensive way. With the development of online academic databases, large-scale academic activity data become available, which implies detailed information on the scholars' achievement and academic activities. Inspired by the recent success of deep graph neural networks (GNNs), we propose a novel solution to recognize high potential scholars on the dynamic heterogeneous academic network. Specifically, we propose a novel Mate-path Hierarchical Heterogeneous Graph Convolution Network (MHHGCN) to effectively model the heterogeneous graph information. MHHGCN hierarchically aggregates entity and relational information on a set of meta-paths, and can alleviate the information loss problem in the previous heterogenous GNN models. Then to capture the dynamic scholar feature, we combine MHHGCN with Long Short Term Memory (LSTM) network with attention mechanism to model the temporal information and predict the potential scholar. Extensive experimental results on real-world high potential scholar data demonstrate the effectiveness of our approach. Moreover, the model shows high interpretability by visualization of the attention layers.

Multi-view clustering aims at exploiting information from multiple heterogeneous views to promote clustering. Most previous works search for only one optimal clustering based on the predefined clustering criterion, but devising such a criterion that captures what users need is difficult. Due to the multiplicity of multi-view data, we can have meaningful alternative clusterings. In addition, the incomplete multi-view data problem is ubiquitous in real world but has not been studied for multiple clusterings. To address these issues, we introduce a deep incomplete multi-view multiple clusterings (DiMVMC) framework, which achieves the completion of data view and multiple shared representations simultaneously by optimizing multiple groups of decoder deep networks. In addition, it minimizes a redundancy term to simultaneously %uses Hilbert-Schmidt Independence Criterion (HSIC) to control the diversity among these representations and among parameters of different networks. Next, it generates an individual clustering from each of these shared representations. Experiments on benchmark datasets confirm that DiMVMC outperforms the state-of-the-art competitors in generating multiple clusterings with high diversity and quality., Comment: 10 pages, ICDM2020

In today's information and computational society, complex systems are often modeled as multi-modal networks associated with heterogeneous structural relation, unstructured attribute/content, temporal context, or their combinations. The abundant information in multi-modal network requires both a domain understanding and large exploratory search space when doing feature engineering for building customized intelligent solutions in response to different purposes. Therefore, automating the feature discovery through representation learning in multi-modal networks has become essential for many applications. In this tutorial, we systematically review the area of multi-modal network representation learning, including a series of recent methods and applications. These methods will be categorized and introduced in the perspectives of unsupervised, semi-supervised and supervised learning, with corresponding real applications respectively. In the end, we conclude the tutorial and raise open discussions. The authors of this tutorial are active and productive researchers in this area.

Cross-lingual entity alignment aims at associating semantically similar entities in knowledge graphs with different languages. It has been an essential research problem for knowledge integration and knowledge graph connection, and been studied with supervised or semi-supervised machine learning methods with the assumption of clean labeled data. However, labels from human annotations often include errors, which can largely affect the alignment results. We thus aim to formulate and explore the robust entity alignment problem, which is non-trivial, due to the deficiency of noisy labels. Our proposed method named REA (Robust Entity Alignment) consists of two components: noise detection and noise-aware entity alignment. The noise detection is designed by following the adversarial training principle. The noise-aware entity alignment is devised by leveraging graph neural network based knowledge graph encoder as the core. In order to mutually boost the performance of the two components, we propose a unified reinforced training strategy to combine them. To evaluate our REA method, we conduct extensive experiments on several real-world datasets. The experimental results demonstrate the effectiveness of our proposed method and also show that our model consistently outperforms the state-of-the-art methods with significant improvement on alignment accuracy in the noise-involved scenario.

Beach litter assessments rely on time inefficient and high human cost protocols, mining the attainment of global beach litter estimates. Here we show the application of an emerging technique, the use of drones for acquisition of high-resolution beach images coupled with machine learning for their automatic processing, aimed at achieving the first national-scale beach litter survey completed by only one operator. The aerial survey had a time efficiency of 570 ± 40 m2 min−1 and the machine learning reached a mean (±SE) detection sensitivity of 59 ± 3% with high resolution images. The resulting mean (±SE) litter density on Saudi Arabian shores of the Red Sea is of 0.12 ± 0.02 litter items m−2, distributed independently of the population density in the area around the sampling station. Instead, accumulation of litter depended on the exposure of the beach to the prevailing wind and litter composition differed between islands and the main shore, where recreational activities are the major source of anthropogenic debris.

Multi-view, Multi-instance, and Multi-label Learning (M3L) can model complex objects (bags), which are represented with different feature views, made of diverse instances, and annotated with discrete non-exclusive labels. Existing M3L approaches assume a complete correspondence between bags and views, and also assume a complete annotation for training. However, in practice, neither the correspondence between bags, nor the bags' annotations are complete. To tackle such a weakly-supervised M3L task, a solution called WSM3L is introduced. WSM3L adapts multimodal dictionary learning to learn a shared dictionary (representational space) across views and individual encoding vectors of bags for each view. The label similarity and feature similarity of encoded bags are jointly used to match bags across views. In addition, it replenishes the annotations of a bag based on the annotations of its neighborhood bags, and introduces a dispatch and aggregation term to dispatch bag-level annotations to instances and to reversely aggregate instance-level annotations to bags. WSM3L unifies these objectives and processes in a joint objective function to predict the instance-level and bag-level annotations in a coordinated fashion, and it further introduces an alternative solution for the objective function optimization. Extensive experimental results show the effectiveness of WSM3L on benchmark datasets.

Crowdsourcing is an economic and efficient strategy aimed at collecting annotations of data through an online platform. Crowd workers with different expertise are paid for their service, and the task requester usually has a limited budget. How to collect reliable annotations for multilabel data and how to compute the consensus within budget are an interesting and challenging, but rarely studied, problem. In this article, we propose a novel approach to accomplish active multilabel crowd consensus (AMCC). AMCC accounts for the commonality and individuality of workers and assumes that workers can be organized into different groups. Each group includes a set of workers who share a similar annotation behavior and label correlations. To achieve an effective multilabel consensus, AMCC models workers’ annotations via a linear combination of commonality and individuality and reduces the impact of unreliable workers by assigning smaller weights to their groups. To collect reliable annotations with reduced cost, AMCC introduces an active crowdsourcing learning strategy that selects sample–label–worker triplets. In a triplet, the selected sample and label are the most informative for the consensus model, and the selected worker can reliably annotate the sample at a low cost. Our experimental results on multilabel data sets demonstrate the advantages of AMCC over state-of-the-art solutions on computing crowd consensus and on reducing the budget by choosing cost-effective triplets.

International audience; The vehicular announcement network is one of the most promising utilities in the communications of smart vehicles and in the smart transportation systems. In general, there are two major issues in building an effective vehicular announcement network. First, it is difficult to forward reliable announcements without revealing users' identities. Second, users usually lack the motivation to forward announcements. In this paper, we endeavor to resolve these two issues through proposing an effective announcement network called CreditCoin, a novel privacy-preserving incentive announcement network based on Blockchain via an efficient anonymous vehicular announcement aggregation protocol. On the one hand, CreditCoin allows nondeterministic different signers (i.e., users) to generate the signatures and to send announcements anonymously in the nonfully trusted environment. On the other hand, with Blockchain, CreditCoin motivates users with incentives to share traffic information. In addition, transactions and account information in CreditCoin are tamper-resistant. CreditCoin also achieves conditional privacy since Trace manager in CreditCoin traces malicious users' identities in anonymous announcements with related transactions. CreditCoin thus is able to motivate users to forward announcements anonymously and reliably. Extensive experimental results show that CreditCoin is efficient and practical in simulations of smart transportation

Point-of-interest (POI) recommendation has attracted much interest recently because of its significant business potential. Data used in POI recommendation (e.g., user-location check-in matrix) are much more sparse than that used in traditional item (e.g., book and movie) recommendation, which leads to more serious cold start problem. Social POI recommendation has proved to be an effective solution, but most existing works assume that recommenders have access to all required data. This is very rare in practice because these data are generally owned by different entities who are not willing to share their data with others due to privacy and legal concerns. In this paper, we first propose PLAS, a protocol which enables effective POI recommendation without disclosing the sensitive data of every party getting involved in the recommendation. We formally show PLAS is secure in the semi-honest adversary model. To improve its performance. We then adopt the technique of cloaking area by which expensive distance computation over encrypted data is replaced by cheap operation over plaintext. In addition, we utilize the sparsity of check-ins to selectively publish data, thus reducing encryption cost and avoiding unnecessary computation over ciphertext. Experiments on two real datasets show that our protocol is feasible and can scale to large POI recommendation problems in practice.

Anomaly intrusion detection in big data environments calls for lightweight models that are able to achieve real-time performance during detection. Abstracting audit data provides a solution to improve the efficiency of data processing in intrusion detection. Data abstraction refers to abstract or extract the most relevant information from the massive dataset. In this work, we propose three strategies of data abstraction, namely, exemplar extraction, attribute selection and attribute abstraction. We first propose an effective method called exemplar extraction to extract representative subsets from the original massive data prior to building the detection models. Two clustering algorithms, Affinity Propagation (AP) and traditional k-means, are employed to find the exemplars from the audit data. k-Nearest Neighbor (k-NN), Principal Component Analysis (PCA) and one-class Support Vector Machine (SVM) are used for the detection. We then employ another two strategies, attribute selection and attribute extraction, to abstract audit data for anomaly intrusion detection. Two http streams collected from a real computing environment as well as the KDD’99 benchmark data set are used to validate these three strategies of data abstraction. The comprehensive experimental results show that while all the three strategies improve the detection efficiency, the AP-based exemplar extraction achieves the best performance of data abstraction.

Android platform has dominated the operating system of mobile devices. However, the dramatic increase of Android malicious applications (malapps) has caused serious software failures to Android system and posed a great threat to users. The effective detection of Android malapps has thus become an emerging yet crucial issue. Characterizing the behaviors of Android applications (apps) is essential to detecting malapps. Most existing works on detecting Android malapps were mainly based on string static features, such as permissions and API usage extracted from apps. There also exists work on the detection of Android malapps with structural features, such as control flow graph and data flow graph. As Android malapps have become increasingly polymorphic and sophisticated, using only one type of static features may result in false negatives. In this paper, we propose DroidEnsemble that takes advantages of both string features and structural features to systematically and comprehensively characterize the static behaviors of Android apps and thus build a more accurate detection model for the detection of Android malapps. We extract each app’s string features, including permissions, hardware features, filter intents, restricted API calls, used permissions, code patterns, as well as structural features like function call graph. We then use three machine learning algorithms, namely, support vector machine, k-nearest neighbor, and random forest, to evaluate the performance of these two types of features and of their ensemble. In the experiments, we evaluate our methods and models with 1386 benign apps and 1296 malapps. Extensive experimental results demonstrate the effectiveness of DroidEnsemble. It achieves the detection accuracy as 95.8% with only string features and as 90.68% with only structural features. DroidEnsemble reaches the detection accuracy as 98.4% with the ensemble of both types of features, reducing 9 false positives and 12 false negatives compared to the results with only string features.

Point-of-interest (POI) recommendation has attracted many interests recently because of its significant potential for helping users to explore new places and helping location-based service (LBS) providers to carry out precision marketing. Compared with the user-item rating matrix in conventional recommender systems, the user-location check-in matrix in POI recommendation is usually much more sparse, which makes the notorious cold start problem more prominent in POI recommendation. Trust-oriented recommendation is an effective way to deal with this problem but it requires that the recommender has access to user check-in and trust data. In practice, however, these data are usually owned by different businesses who are not willing to share their data with the recommender mainly due to privacy and legal concerns. In this paper, we propose a privacy-preserving framework to boost data owners willingness to share their data with untrustworthy businesses. More specifically, we utilize partially homomorphic encryption to design two protocols for privacy-preserving trust-oriented POI recommendation. By offline encryption and parallel computing, these protocols can efficiently protect the private data of every party involved in the recommendation. We prove that the proposed protocols are secure against semi-honest adversaries. Experiments on both synthetic data and real data show that our protocols can achieve privacy-preserving with acceptable computation and communication cost.

Social discrimination is said to occur when an unfavorable decision for an individual is influenced by her membership to certain protected groups such as females and minority ethnic groups. Such discriminatory decisions often exist in historical data. Despite recent works in discrimination-aware data mining, there remains the need for robust, yet easily usable, methods for discrimination control. In this paper, we utilize reject option in classification, a general decision theoretic framework for handling instances whose labels are uncertain, for modeling and controlling discriminatory decisions. Specifically, this framework permits a formal treatment of the intuition that instances close to the decision boundary are more likely to be discriminated in a dataset. Based on this framework, we present three different solutions for discrimination-aware classification. The first solution invokes probabilistic rejection in single or multiple probabilistic classifiers while the second solution relies upon ensemble rejection in classifier ensembles. The third solution integrates one of the first two solutions with situation testing which is a procedure commonly used in the court of law. All solutions are easy to use and provide strong justifications for the decisions. We evaluate our solutions extensively on four real-world datasets and compare their performances with previously proposed discrimination-aware classifiers. The results demonstrate the superiority of our solutions in terms of both performance and flexibility of applicability. In particular, our solutions are effective at removing illegal discrimination from the predictions. (C) 2017 Published by Elsevier Inc.

Android platform has dominated the markets of smart mobile devices in recent years. The number of Android applications (apps) has seen a massive surge. Unsurprisingly, Android platform has also become the primary target of attackers. The management of the explosively expansive app markets has thus become an important issue. On the one hand, it requires effectively detecting malicious applications (malapps) in order to keep the malapps out of the app market. On the other hand, it needs to automatically categorize a big number of benign apps so as to ease the management, such as correcting an apps category falsely designated by the app developer. In this work, we propose a framework to effectively and efficiently manage a big app market in terms of detecting malapps and categorizing benign apps. We extract 11 types of static features from each app to characterize the behaviors of the app, and employ the ensemble of multiple classifiers, namely, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naive Bayes (NB), Classification and Regression Tree (CART) and Random Forest (RF), to detect malapps and to categorize benign apps. An alarm will be triggered if an app is identified as malicious. Otherwise, the benign app will be identified as a specific category. We evaluate the framework on a large app set consisting of 107,327 benign apps as well as 8,701 malapps. The experimental results show that our method achieves the accuracy of 99.39% in the detection of malapps and achieves the best accuracy of 82.93% in the categorization of benign apps. First work to provide a complete solution for automated categorization of apps.Extract 23,74,340 features from each APK file.Use ensemble of multiple classifiers to improve the detection accuracy.Use large data sets containing 107,327 benign apps and 8701 malapps for testing.Reach detection accuracy as 99.39% and categorization accuracy as 82.93%.

The tunnel junction (TJ) is a crucial structure for numerous III-nitride devices. A fundamental challenge for TJ design is to minimize the TJ resistance at high current densities. In this work, we propose the asymmetric p-AlGaN/i-InGaN/n-AlGaN TJ structure for the first time. P-AlGaN/i-InGaN/n-AlGaN TJs were simulated with different Al or In compositions and different InGaN layer thicknesses using TCAD (Technology Computer-Aided Design) software. Trained by these data, we constructed a highly efficient model for TJ resistance prediction using machine learning. The model constructs a tool for real-time prediction of the TJ resistance, and the resistances for 22,254 different TJ structures were predicted. Based on our TJ predictions, the asymmetric TJ structure (p-Al0.7Ga0.3N/i-In0.2Ga0.8N/n-Al0.3Ga0.7N) with higher Al composition in p-layer has seven times lower TJ resistance compared to the prevailing symmetric p-Al0.3Ga0.7N/i-In0.2Ga0.8N/n-Al0.3Ga0.7N TJ. This study paves a new way in III-nitride TJ design for optical and electronic devices.

Up-to-date report on the accuracy and efficiency of state-of-the-art classifiers.We compare the accuracy of 11 classification algorithms pairwise and groupwise.We examine separately the training, parameter-tuning, and testing time.GBDT and Random Forests yield highest accuracy, outperforming SVM.GBDT is the fastest in testing, Naive Bayes the fastest in training. Current benchmark reports of classification algorithms generally concern common classifiers and their variants but do not include many algorithms that have been introduced in recent years. Moreover, important properties such as the dependency on number of classes and features and CPU running time are typically not examined. In this paper, we carry out a comparative empirical study on both established classifiers and more recently proposed ones on 71 data sets originating from different domains, publicly available at UCI and KEEL repositories. The list of 11 algorithms studied includes Extreme Learning Machine (ELM), Sparse Representation based Classification (SRC), and Deep Learning (DL), which have not been thoroughly investigated in existing comparative studies. It is found that Stochastic Gradient Boosting Trees (GBDT) matches or exceeds the prediction performance of Support Vector Machines (SVM) and Random Forests (RF), while being the fastest algorithm in terms of prediction efficiency. ELM also yields good accuracy results, ranking in the top-5, alongside GBDT, RF, SVM, and C4.5 but this performance varies widely across all data sets. Unsurprisingly, top accuracy performers have average or slow training time efficiency. DL is the worst performer in terms of accuracy but second fastest in prediction efficiency. SRC shows good accuracy performance but it is the slowest classifier in both training and testing.

Android malicious applications (malapps) have surged and been sophisticated, posing a great threat to users. How to characterize, understand and detect Android malapps at a large scale is thus a big challenge. In this work, we are motivated to discover the discriminatory and persistent features extracted from Android APK files for automated malapp detection at a large scale. To achieve this goal, firstly we extract a very large number of features from each app and categorize the features into two groups, namely, app-specific features as well as platform-defined features. These feature sets will then be fed into four classifiers (i.e., Logistic Regression, linear SVM, Decision Tree and Random Forest) for the detection of malapps. Secondly, we evaluate the persistence of app-specific and platform-defined features on classification performance with two data sets collected in different time periods. Thirdly, we comprehensively analyze the relevant features selected by Logistic Regression classifier to identify the contributions of each feature set. We conduct extensive experiments on large real-world app sets consisting of 213,256 benign apps collected from six app markets, 4,363 benign apps from Google Play market, and 18,363 malapps. The experimental results and our analysis give insights regarding what discriminatory features are most effective to characterize malapps for building an effective and efficient malapp detection system. With the selected discriminatory features, the Logistic Regression classifier yields the best true positive rate as 96% with a false positive rate as 0.06%.

Data repairing aims at discovering and correcting erroneous data in databases. In this paper, we develop Web-ADARE, an end-to-end web-aided data repairing system, to provide a feasible way to involve the vast data sources on the Web in data repairing. Our main attention in developing Web-ADARE is paid on the interaction problem between web-aided repairing and rule-based repairing, in order to minimize the Web consultation cost while reaching predefined quality requirements. The same interaction problem also exists in crowd-based methods but this is not yet formally defined and addressed. We first prove in theory that the optimal interaction scheme is not feasible to be achieved, and then propose an algorithm to identify a scheme for efficient interaction by investigating the inconsistencies and the dependencies between values in the repairing process. Extensive experiments on three data collections demonstrate the high repairing precision and recall of Web-ADARE, and the efficiency of the generated interaction scheme over several baseline ones.

Spatial crowdsourcing (SC) outsources tasks to a set of workers who are required to physically move to specified locations and accomplish tasks. Recently, it is emerging as a promising tool for emergency management, as it enables efficient and cost-effective collection of critical information in emergency such as earthquakes, when search and rescue survivors in potential ares are required. However in current SC systems, task locations and worker locations are all exposed in public without any privacy protection. SC systems if attacked thus have penitential risk of privacy leakage. In this paper, we propose a protocol for protecting the privacy for both workers and task requesters while maintaining the functionality of SC systems. The proposed protocol is built on partially homomorphic encryption schemes, and can efficiently realize complex operations required during task assignment over encrypted data through a well-designed computation strategy. We prove that the proposed protocol is privacy-preserving against semi-honest adversaries. Simulation on two real-world datasets shows that the proposed protocol is more effective than existing solutions and can achieve mutual privacy-preserving with acceptable computation and communication cost.

Recent developments in sensors, global positioning system devices, and smart phones have increased the availability of spatiotemporal data streams. Developing models for mining such streams is challenged by the huge amount of data that cannot be stored in the memory, the high arrival speed, and the dynamic changes in the data distribution. Density estimation is an important technique in stream mining for a wide variety of applications. The construction of kernel density estimators is well studied and documented. However, existing techniques are either expensive or inaccurate and unable to capture the changes in the data distribution. In this paper, we present a method called KDE-Track to estimate the density of spatiotemporal data streams. KDE-Track can efficiently estimate the density function with linear time complexity using interpolation on a kernel model, which is incrementally updated upon the arrival of new samples from the stream. We also propose an accurate and efficient method for selecting the bandwidth value for the kernel density estimator, which increases its accuracy significantly. Both theoretical analysis and experimental validation show that KDE-Track outperforms a set of baseline methods on the estimation accuracy and computing time of complex density structures in data streams.

In the real world, the route/path with the shortest travel time in a road network is more meaningful than that with the shortest network distance for location-based services (LBS). However, not every LBS provider has adequate resources to compute/estimate travel time for routes by themselves. A cost-effective way for LBS providers to estimate travel time for routes is to issue external route requests to Web mapping services (e.g., Google Maps, Bing Maps, and MapQuest Maps). Due to the high cost of processing such external route requests and the usage limits of Web mapping services, we take the advantage of direction sharing, parallel requesting and waypoints supported by Web mapping services to reduce the number of external route requests and the query response time for shortest travel-time route queries in this paper. We first give the definition of sharing ability to reflect the possibility of sharing the direction information of a route with others, and find out the queries that their query routes are independent with each other for parallel processing. Then, we model the problem of selecting the optimal waypoints for an external route request as finding the longest simple path in a weighted complete digraph. As it is a MAX SNP-hard problem, we propose a greedy algorithm with performance guarantee to find the best set of waypoints in an external route request. We evaluate the performance of our approach using a real Web mapping service, a real road network, real and synthetic data sets. Experimental results show the efficiency, scalability, and applicability of our approach.

Schema Matching (SM) and Record Matching (RM) are two necessary steps in integrating multiple relational tables of different schemas, where SM unifies the schemas and RM detects records referring to the same real-world entity. The two processes have been thoroughly studied separately, but few attention has been paid to the interaction of SM and RM. In this work, we find that, even alternating them in a simple manner, SM and RM can benefit from each other to reach a better integration performance (i.e., in terms of precision and recall). Therefore, combining SM and RM is a promising solution for improving data integration. To this end, we define novel matching rules for SM and RM, respectively, that is, every SM decision is made based on intermediate RM results, and vice versa, such that SM and RM can be performed alternately. The quality of integration is guaranteed by a Matching Likelihood Estimation model and the control of semantic drift, which prevent the effect of mismatch magnification. To reduce the computational cost, we design an index structure based on q-grams and a greedy search algorithm that can reduce around 90 percent overhead of the interaction. Extensive experiments on three data collections show that the combination and interaction between SM and RM significantly outperforms previous works that conduct SM and RM separately.

Cross-lingual entity alignment identifies entity pairs that share the same meanings but locate in different language knowledge graphs (KGs). The study in this paper is to address two limitations that widely exist in current solutions: 1) the alignment loss functions defined at the entity level serve well the purpose of aligning labeled entities but fail to match the whole picture of labeled and unlabeled entities in different KGs; 2) the translation from one domain to the other has been considered (e.g., X to Y by M1 or Y to X by M2). However, the important duality of alignment between different KGs (X to Y by M1 and Y to X by M2) is ignored. We propose a novel entity alignment framework (OTEA), which dually optimizes the entity-level loss and group-level loss via optimal transport theory. We also impose a regularizer on the dual translation matrices to mitigate the effect of noise during transformation. Extensive experimental results show that our model consistently outperforms the state-of-the-arts with significant improvements on alignment accuracy.

Hashing has been widely studied for big data retrieval due to its low storage cost and fast query speed. Zero-shot hashing (ZSH) aims to learn a hashing model that is trained using only samples from seen categories, but can generalize well to samples of unseen categories. ZSH generally uses category attributes to seek a semantic embedding space to transfer knowledge from seen categories to unseen ones. As a result, it may perform poorly when labeled data are insufficient. ZSH methods are mainly designed for single-modality data, which prevents their application to the widely spread multi-modal data. On the other hand, existing cross-modal hashing solutions assume that all the modalities share the same category labels, while in practice the labels of different data modalities may be different. To address these issues, we propose a general Cross-modal Zero-shot Hashing (CZHash) solution to effectively leverage unlabeled and labeled multi-modality data with different label spaces. CZHash first quantifies the composite similarity between instances using label and feature information. It then defines an objective function to achieve deep feature learning compatible with the composite similarity preserving, category attribute space learning, and hashing coding function learning. CZHash further introduces an alternative optimization procedure to jointly optimize these learning objectives. Experiments on benchmark multi-modal datasets show that CZHash significantly outperforms related representative hashing approaches both on effectiveness and adaptability.

Task appearance prediction has great potential to improve task assignment in spatial crowdsourcing platforms. The main challenge of this prediction problem is to model the spatial dependency among neighboring regions and the temporal dependency at different time scales (e.g., hourly, daily, and weekly). A recent model ST-ResNet predicts traffic flow by capturing the spatial and temporal dependencies in historical data. However, the data fragments are concatenated as one tensor fed to the deep neural networks, rather than learning the temporal dependencies in a sequential manner. We propose a novel deep learning model, called SeqST-ResNet, which well captures the temporal dependencies of historical task appearance in sequences at several time scales. We validate the effectiveness of our model via experiments on a real-world dataset. The experimental results show that our SeqST-ResNet model significantly outperforms ST-ResNet when predicting tasks at hourly intervals and also during weekday and weekends, more importantly, in regions with intensive task requests.

With the advances in technology and smart devices, more and more attention has been paid to model spatial correlations, temporal dynamics, and friendship influence over point-of-interest (POI) checkins. Besides directly capturing general user’s checkin behavior, existing works mostly highlight the intrinsic feature of POIs, i.e., spatial and temporal dependency. Among them, the family of methods based on Markov chain can capture the instance-level interaction between a pair of POI checkins, while recurrent neural network (RNN) based approaches (state-of-the-art) can deal with flexible length of checkin sequence. However, the former is not good at capturing high-order POI transition dependency, and the latter cannot distinguish the exact contribution of each POI in a historical checkin sequence. Moreover, in recurrent neural networks, local and global information is propagated along the sequence through one bottleneck i.e., hidden states only.In this work, we design a novel model to enforce contextual constraints on sequential data by designing a spatial and temporal attention mechanisms over recurrent neural network that leverages the importance of POIs visited by users in given time interval and geographical distance in successive checkins. Attention mechanism helps us to learn which POIs bounded by time difference and spatial distance in user checkin history are important for the prediction of next POI. Moreover, we also consider periodicity and friendship influence in our model design. Experimental results on two real location based social networks Gowalla, and BrightKite show that our proposed method outperforms the existing state-of-the-art deep neural network methods for next POI prediction and understanding user transition behavior. We also analyze the sensitivity of parameters including context window for capturing sequential effect, temporal context window for estimating temporal attention and spatial context window for estimating spatial attention respectively.

Finding popular datasets to work on is essential for data-driven research domains. In this paper, we focus on the problem of extracting top-k popular datasets that have been used in data mining, machine learning, and artificial intelligence fields. We solve this problem on an attributed citation network, which includes node content information (text of published papers) and paper citation relations. By formulating the problem as a semi-supervised multi-label classification one, we develop an efficient deep generative model for learning from both the document content and citation relations. The evaluation on a real-world dataset shows that our proposed model outperforms baseline methods. We then apply the model further to reveal the top-k frequently cited datasets in selected areas and report interesting findings.

Crowdsensed Data Trading (CDT) is a novel data trading paradigm, where each data consumer can publicize its data demand as some crowdsensing tasks, and some mobile users (i.e., data sellers) can compete for these tasks, collect the corresponding data, and sell the results to the consumers. Existing CDT systems generally depend on a data trading broker, which will inevitably cause consumers concerns on the trustworthiness of the systems and truthfulness of the data. To address this problem, we propose a Blockchain-based Crowdsensed Data Trading (BCDT) system, mainly containing a smart contract, called BCDToken. First, we replace the broker with blockchain to guarantee the trustworthiness of data trading. Meanwhile, BCDToken adopts Blockchain-based Reverse Auction (BRA) to assign tasks to data sellers. BRA holds truthfulness and individual rationality, which can ensure the sellers to report costs honestly and prevent sellers to manipulate the auction. Moreover, we implement a Secure Truth Discovery and reliability Rating (STDR) mechanism in BCDToken based on homomorphic cryptography, which can incentivize sellers to upload the truthful data and consumers to rate truthfully the reliabilities of sellers without revealing any privacy of data. Additionally, we also deploy BCDToken to the test network to demonstrate its practicability.

This paper solves the problem of providing high-quality suggestions for user keyword queries over databases. With the assumption that the returned suggestions are independent, existing query suggestion methods over databases score candidate suggestions individually and return the top-k best of them. However, the top-k suggestions have high redundancy with respect to the topics. To provide informative suggestions, the returned k suggestions are expected to be diverse, i.e., maximizing the relevance to the user query and the diversity with respect to topics that the user might be interested in simultaneously. In this paper, an objective function considering both factors is defined for evaluating a suggestion set. We show that maximizing the objective function is a submodular function maximization problem subject to n matroid constraints, which is an NP-hard problem. An greedy approximate algorithm with an approximation ratio O(11+n$\frac {1}{1+n}$) is also proposed. Experimental results show that our suggestion outperforms other methods on providing relevant and diverse suggestions.

Alzheimer's Disease (AD) is currently attracting much attention in elders' care. As the increasing availability of massive clinical diagnosis data, especially the medical images of brain scan, it is highly significant to precisely identify and predict the potential AD's progression based on the knowledge in the diagnosis data. In this paper, we follow a novel sequential learning framework to model the disease progression for AD patients' care. Different from the conventional approaches using only initial or static diagnosis data to model the disease progression for different durations, we design a score-involved approach and make use of the sequential diagnosis information in different disease stages to jointly simulate the disease progression. The actual clinical scores are utilized in progress to make the prediction more pertinent and reliable. We examined our approach by extensive experiments on the clinical data provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI). The results indicate that the proposed approach is more effective to simulate and predict the disease progression compared with the existing methods.

Classification with indefinite similarities has attracted attention in the machine learning community. This is partly due to the fact that many similarity functions that arise in practice are not symmetric positive semidefinite, i.e. the Mercer condition is not satisfied, or the Mercer condition is difficult to verify. Examples of such indefinite similarities in machine learning applications are ample including, for instance, the BLAST similarity score between protein sequences, human-judged similarities between concepts and words, and the tangent distance or the shape matching distance in computer vision. Nevertheless, previous works on classification with indefinite similarities are not fully satisfactory. They have either introduced sources of inconsistency in handling past and future examples using kernel approximation, settled for local-minimum solutions using non-convex optimization, or produced non-sparse solutions by learning in Krein spaces. Despite the large volume of research devoted to this subject lately, we demonstrate in this paper how an old idea, namely the 1-norm support vector machine (SVM) proposed more than 15 years ago, has several advantages over more recent work. In particular, the 1-norm SVM method is conceptually simpler, which makes it easier to implement and maintain. It is competitive, if not superior to, all other methods in terms of predictive accuracy. Moreover, it produces solutions that are often sparser than more recent methods by several orders of magnitude. In addition, we provide various theoretical justifications by relating 1-norm SVM to well-established learning algorithms such as neural networks, SVM, and nearest neighbor classifiers. Finally, we conduct a thorough experimental evaluation, which reveals that the evidence in favor of 1-norm SVM is statistically significant.

Tremendous efforts have been dedicated to improving the effectiveness of multi-label learning with incomplete label assignments. Most of the current techniques assume that the input features of data instances are complete. Nevertheless, the co-occurrence of highly incomplete features and weak label assignments is a challenging and widely perceived issue in real-world multi-label learning applications due to a number of practical reasons including incomplete data collection, moderate labels from annotators, etc. Existing multi-label learning algorithms are not directly applicable when the observed features are highly incomplete. In this work, we attack this problem by proposing a weakly supervised multi-label learning approach, based on the idea of collaborative embedding. This approach provides a flexible framework to conduct efficient multi-label classification at both transductive and inductive mode by coupling the process of reconstructing missing features and weak label assignments in a joint optimisation framework. It is designed to collaboratively recover feature and label information, and extract the predictive association between the feature profile and the multi-label tag of the same data instance. Substantial experiments on public benchmark datasets and real security event data validate that our proposed method can provide distinctively more accurate transductive and inductive classification than other state-of-the-art algorithms.

In this paper, we study the problem of dynamic user profiling in Twitter. We address the problem by proposing a dynamic user and word embedding model (DUWE), a scalable black-box variational inference algorithm, and a streaming keyword diversification model (SKDM). DUWE dynamically tracks the semantic representations of users and words over time and models their embeddings in the same space so that their similarities can be effectively measured. Our inference algorithm works with a convex objective function that ensures the robustness of the learnt embeddings. SKDM aims at retrieving top-K relevant and diversified keywords to profile users' dynamic interests. Experiments on a Twitter dataset demonstrate that our proposed embedding algorithms outperform state-of-the-art non-dynamic and dynamic embedding and topic models.