Search

Recently we have seen a rapid rise in the amount of education data available through the digitization of education. This huge amount of education data usually exhibits in a mixture form of images, videos, speech, texts, etc. It is crucial to consider data from different modalities to build successful applications in AI in education (AIED). This tutorial targets AI researchers and practitioners who are interested in applying state-of-the-art multimodal machine learning techniques to tackle some of the hard-core AIED tasks. These include tasks such as automatic short answer grading, student assessment, class quality assurance, knowledge tracing, etc. In this tutorial, we will comprehensively review recent developments of applying multimodal learning approaches in AIED, with a focus on those classroom multimodal data. Beyond introducing the recent advances of computer vision, speech, natural language processing in education respectively, we will discuss how to combine data from different modalities and build AI driven educational applications on top of these data. More specifically, we will talk about (1) representation learning; (2) algorithmic assessment & evaluation; and (3) personalized feedback. Participants will learn about recent trends and emerging challenges in this topic, representative tools and learning resources to obtain ready-to-use models, and how related models and techniques benefit real-world AIED applications.

Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples leaves us a big hesitation when applying DNN models on safety-critical tasks such as autonomous vehicles and malware detection. These adversarial examples are intentionally crafted instances, either appearing in the train or test phase, which can fool the DNN models to make severe mistakes. Therefore, people are dedicated to devising more robust models to resist adversarial examples, but usually they are broken by new stronger attacks. This arms-race between adversarial attacks and defenses has been drawn increasing attention in recent years. In this tutorial, we provide a comprehensive overview on the frontiers and advances of adversarial attacks and their countermeasures. In particular, we give a detailed introduction of different types of attacks under different scenarios, including evasion and poisoning attacks, white-box and black box attacks. We will also discuss how the defending strategies develop to compete against these attacks, and how new attacks come out to break these defenses. Moreover, we will discuss the story of adversarial attacks and defenses in other data domains, especially in graph structured data. Then, we introduce DeepRobust, a Pytorch adversarial learning library which aims to build a comprehensive and easy-to-use platform to foster this research field. Finally, we summarize the tutorial with discussions on open issues and challenges about adversarial attacks and defenses. Via our tutorial, our audience can grip the main idea and key approaches of the game between adversarial attacks and defenses.

Increasingly many teachers are turning to online social media to supplement educational resources and meet students' needs in the classrooms. The diffusion of information from online social media to the classroom is significantly faster than traditional curriculum-based approaches. However, this is contingent upon how well teachers across an online social media network are connected. To understand this, we perform a thorough and large-scale investigation of teacher connections in online social media, which is lacking in the literature. To make this feasible, we construct a large dataset of teachers on Pinterest, an image-based popular online social media. Our dataset includes 540 teachers across 5 states and 48 districts, thousands of connections they have established (either with their peers or some other Pinterest users), and all the resources they have shared in their accounts. Then, taking into account some crucial teacher-related attributes (e.g., their districts, grade levels, etc), we characterize direct and indirect teacher connections. Moreover, we compare the physical (face to face) and virtual (Pinterest) network of our surveyed teachers using several graph-related metrics. The finding in this study can serve as a basis to investigate teachers on social media in a deeper manner.

Graphs are used to model pairwise relations between entities in many real-world scenarios such as social networks. Graph Neural Networks(GNNs) have shown their superior ability in learning representations for graph structured data, which leads to performance improvements in many graph related tasks such as link prediction, node classification and graph classification. Most of the existing graph neural networks models are designed for static graphs while many real-world graphs are inherently dynamic with new nodes and edges constantly emerging. Existing graph neural network models cannot utilize the dynamic information, which has been shown to enhance the performance of many graph analytic tasks such as community detection. Hence, in this paper, we propose DyGNN, a Dynamic Graph Neural Network model, which can model the dynamic information as the graph evolving. In particular, the proposed framework keeps updating node information by capturing the sequential information of edges (interactions), the time intervals between edges and information propagation coherently. Experimental results on various dynamic graphs demonstrate the effectiveness of the proposed framework.

Deep recommender systems have achieved promising performance on real-world recommendation tasks. They typically represent users and items in a low-dimensional embedding space and then feed the embeddings into the following deep network structures for prediction. Traditional deep recommender models often adopt uniform and fixed embedding sizes for all the users and items. However, such design is not optimal in terms of not only the recommendation performance and but also the space complexity. In this paper, we propose to dynamically search the embedding sizes for different users and items and introduce a novel embedding size adjustment policy network (ESAPN). ESAPN serves as an automated reinforcement learning agent to adaptively search appropriate embedding sizes for users and items. Different from existing works, our model performs hard selection on different embedding sizes, which leads to a more accurate selection and decreases the storage space. We evaluate our model under the streaming setting on two real-world benchmark datasets. The results show that our proposed framework outperforms representative baselines. Moreover, our framework is demonstrated to be robust to the cold-start problem and reduce memory consumption by around 40%-90%. The implementation of the model is released.

Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations, called adversarial attacks. Adversarial attacks can easily fool GNNs in making predictions for downstream tasks. The vulnerability to adversarial attacks has raised increasing concerns for applying GNNs in safety-critical applications. Therefore, developing robust algorithms to defend adversarial attacks is of great significance. A natural idea to defend adversarial attacks is to clean the perturbed graph. It is evident that real-world graphs share some intrinsic properties. For example, many real-world graphs are low-rank and sparse, and the features of two adjacent nodes tend to be similar. In fact, we find that adversarial attacks are likely to violate these graph properties. Therefore, in this paper, we explore these properties to defend adversarial attacks on graphs. In particular, we propose a general framework Pro-GNN, which can jointly learn a structural graph and a robust graph neural network model from the perturbed graph guided by these properties. Extensive experiments on real-world graphs demonstrate that the proposed framework achieves significantly better performance compared with the state-of-the-art defense methods, even when the graph is heavily perturbed. We release the implementation of Pro-GNN to our DeepRobust repository for adversarial attacks and defenses (footnote: https://github.com/DSE-MSU/DeepRobust). The specific experimental settings to reproduce our results can be found in https://github.com/ChandlerBang/Pro-GNN., Accepted by KDD 2020

In real-world networks, nodes might have more than one type of relationship. Signed networks are an important class of such networks consisting of two types of relations: positive and negative. Recently, embedding signed networks has attracted increasing attention and is more challenging than classic networks since nodes are connected by paths with multi-types of links. Existing works capture the complex relationships by relying on social theories. However, this approach has major drawbacks, including the incompleteness/inaccurateness of such theories. Thus, we propose network transformation based embedding to address these shortcomings. The core idea is that rather than directly finding the similarities of two nodes from the complex paths connecting them, we can obtain their similarities through simple paths connecting their different roles. We employ this idea to build our proposed embedding technique that can be described in three steps: (1) the input directed signed network is transformed into an unsigned bipartite network with each node mapped to a set of nodes we denote as role-nodes. Each role-node captures a certain role that a node in the original network plays; (2) the network of role-nodes is embedded; and (3) the original network is encoded by aggregating the embedding vectors of role-nodes. Our experiments show the novel proposed technique substantially outperforms existing models.

Traffic flow analysis, prediction and management are keystones for building smart cities in the new era. With the help of deep neural networks and big traffic data, we can better understand the latent patterns hidden in the complex transportation networks. The dynamic of the traffic flow on one road not only depends on the sequential patterns in the temporal dimension but also relies on other roads in the spatial dimension. Although there are existing works on predicting the future traffic flow, the majority of them have certain limitations on modeling spatial and temporal dependencies. In this paper, we propose a novel spatial temporal graph neural network for traffic flow prediction, which can comprehensively capture spatial and temporal patterns. In particular, the framework offers a learnable positional attention mechanism to effectively aggregate information from adjacent roads. Meanwhile, it provides a sequential component to model the traffic flow dynamics which can exploit both local and global temporal dependencies. Experimental results on various real traffic datasets demonstrate the effectiveness of the proposed framework.

In today’s world, users typically take to online social media to express their opinions, which can inherently be both positive and negative. In fact, online social networks can be best modeled as signed networks, where opinions in the form of positive and negative links can exist between users, such as our friends and foes (e.g., “unfriended” users), respectively. Furthermore, users can also express their opinions to content generated by others through online social interactions, such as commenting or rating. Intuitively, these two types of opinions in the form of links and interactions should be related. For example, users’ interactions are likely to be positive (or negative) to those they have positively (or negatively) established links with. Similarly, we tend to establish positive (or negative) links with those whose generated content we frequently positively (or negatively) interact with online. Hence, in this paper, we first verify these assumptions by understanding the correlation between these two types of opinions from both a local and global perspective. Then, we propose a framework that jointly solves the link and interaction polarity prediction problem based on our newly found understanding of how these two problems are correlated. We ultimately perform experiments on a real-world signed network to demonstrate the effectiveness of our proposed approach to help mitigate both the data sparsity and cold-start problems found in the two tasks of link and interaction polarity prediction.

A growing trend recently is to harness the structure of today's big data, where much of the data can be represented as graphs. Simultaneously, graph convolutional networks (GCNs) have been proposed and since seen rapid development. More recently, due to the scalability issues that arise when attempting to utilize these powerful models on real-world data, methodologies have sought the use of sampling techniques. More specifically, minibatches of nodes are formed and then sets of nodes are sampled to aggregate from in one or more layers. Among these methods, the two prominent ways are based on sampling nodes from either a local or global perspective. In this work, we first observe the similarities in the two sampling strategies to that of epidemic and diffusion network models. Then we harness this understanding to fuse together the benefits of sampling from both a local and global perspective while alleviating some of the inherent issues found in both through the use of a low-dimensional approximation for the path-based Katz similarity measure. Our proposed framework, Epidemic Graph Convolutional Network (EGCN), is thus able to achieve improved performance over sampling from just one of the two perspectives alone. Empirical experiments are performed on several public benchmark datasets to verify the effectiveness over existing methodologies for the node classification task and we furthermore present some empirical parameter analysis of EGCN.

One crucial aspect that yet remains fairly unknown while can inform us about the behavior of deep neural networks is their decision boundaries. Trust can be improved once we understand how and why deep models carve out a particular form of decision boundary and thus make particular decisions. Robustness against adversarial examples is directly related to the decision boundary as adversarial examples are basically 'missed out' by the decision boundary between two classes. Investigating the decision boundary of deep neural networks, nevertheless, faces tremendous challenges. First, how we can generate instances near the decision boundary that are similar to real samples? Second, how we can leverage near decision boundary instances to characterize the behaviour of deep neural networks? Motivated to solve these challenges, we focus on investigating the decision boundary of deep neural network classifiers. In particular, we propose a novel approach to generate instances near decision boundary of pre-trained DNNs and then leverage these instances to characterize the behaviour of deep models.

Many real-world relations can be represented by signed networks with positive links (e.g., friendships and trust) and negative links (e.g., foes and distrust). Link prediction helps advance tasks in social network analysis such as recommendation systems. Most existing work on link analysis focuses on unsigned social networks. The existence of negative links piques research interests in investigating whether properties and principles of signed networks differ from those of unsigned networks, and mandates dedicated efforts on link analysis for signed social networks. Recent findings suggest that properties of signed networks substantially differ from those of unsigned networks and negative links can be of significant help in signed link analysis in complementary ways. In this article, we center our discussion on a challenging problem of signed link analysis. Signed link analysis faces the problem of data sparsity, i.e. only a small percentage of signed links are given. This problem can even get worse when negative links are much sparser than positive ones as users are inclined more towards positive disposition rather than negative. We investigate how we can take advantage of other sources of information for signed link analysis. This research is mainly guided by three social science theories, Emotional Information, Diffusion of Innovations, and Individual Personality. Guided by these, we extract three categories of related features and leverage them for signed link analysis. Experiments show the significance of the features gleaned from social theories for signed link prediction and addressing the data sparsity challenge., This worked is published at ACM Transactions on Intelligent Systems and Technology(ACM TIST), 2019

Online recommendation and advertising are two major income channels for online recommendation platforms (e.g. e-commerce and news feed site). However, most platforms optimize recommending and advertising strategies by different teams separately via different techniques, which may lead to suboptimal overall performances. To this end, in this paper, we propose a novel two-level reinforcement learning framework to jointly optimize the recommending and advertising strategies, where the first level generates a list of recommendations to optimize user experience in the long run; then the second level inserts ads into the recommendation list that can balance the immediate advertising revenue from advertisers and the negative influence of ads on long-term user experience. To be specific, the first level tackles high combinatorial action space problem that selects a subset items from the large item space; while the second level determines three internally related tasks, i.e., (i) whether to insert an ad, and if yes, (ii) the optimal ad and (iii) the optimal location to insert. The experimental results based on real-world data demonstrate the effectiveness of the proposed framework. We have released the implementation code to ease reproductivity., Comment: Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '20), August 23--27, 2020, Virtual Event, CA, USA

Classroom activity detection (CAD) aims at accurately recognizing speaker roles (either teacher or student) in classrooms. A CAD solution helps teachers get instant feedback on their pedagogical instructions. However, CAD is very challenging because (1) classroom conversations contain many conversational turn-taking overlaps between teachers and students; (2) the CAD model needs to be generalized well enough for different teachers and students; and (3) classroom recordings may be very noisy and low-quality. In this work, we address the above challenges by building a Siamese neural framework to automatically identify teacher and student utterances from classroom recordings. The proposed model is evaluated on real-world educational datasets. The results demonstrate that (1) our approach is superior on the prediction tasks for both online and offline classroom environments; and (2) our framework exhibits robustness and generalization ability on new teachers (i.e., teachers never appear in training data).

Many teachers utilize online social media to supplement their students’ needs and enhance their professional activities, curating millions of educational resources. In fact, during the Coronovirus pandemic, online curation of resources provides teachers a repository of materials to provide students in online space. Teachers’ engagement online then provides the ability to learn more about how teachers are addressing students’ learning needs and potentially improve the quality of the resources they share. Historically, to perform such a study, we often survey some teachers and then leverage their shared resources to investigate education-related research questions. However, this can lead to problems including sample representativeness where surveyed teachers may not be representative of the population of teachers in social media. In this paper, we attempt to improve the sample representativeness of teachers on Pinterest. We first survey 541 teachers in the United States as seed samples and then collect their online data and social connections on Pinterest. Then, we devise a heuristic that automatically identifies other Pinterest accounts that are likely to be teachers thus improving the sample representativeness. Finally, we evaluate our heuristic with advanced machine learning techniques.

Graph Convolutional Networks (GCNs) show promising results for semi-supervised learning tasks on graphs, thus become favorable comparing with other approaches. Despite the remarkable success of GCNs, it is difficult to train GCNs with insufficient supervision. When labeled data are limited, the performance of GCNs becomes unsatisfying for low-degree nodes. While some prior work analyze successes and failures of GCNs on the entire model level, profiling GCNs on individual node level is still underexplored. In this paper, we analyze GCNs in regard to the node degree distribution. From empirical observation to theoretical proof, we confirm that GCNs are biased towards nodes with larger degrees with higher accuracy on them, even if high-degree nodes are underrepresented in most graphs. We further develop a novel Self-Supervised-Learning Degree-Specific GCN (SL-DSGC) that mitigate the degree-related biases of GCNs from model and data aspects. Firstly, we propose a degree-specific GCN layer that captures both discrepancies and similarities of nodes with different degrees, which reduces the inner model-aspect biases of GCNs caused by sharing the same parameters with all nodes. Secondly, we design a self-supervised-learning algorithm that creates pseudo labels with uncertainty scores on unlabeled nodes with a Bayesian neural network. Pseudo labels increase the chance of connecting to labeled neighbors for low-degree nodes, thus reducing the biases of GCNs from the data perspective. Uncertainty scores are further exploited to weight pseudo labels dynamically in the stochastic gradient descent for SL-DSGC. Experiments on three benchmark datasets show SL-DSGC not only outperforms state-of-the-art self-training/self-supervised-learning GCN methods, but also improves GCN accuracy dramatically for low-degree nodes., Comment: Accepted to CIKM 2020

Representation learning has been proven to play an important role in the unprecedented success of machine learning models in numerous tasks, such as machine translation, face recognition and recommendation. The majority of existing representation learning approaches often require a large number of consistent and noise-free labels. However, due to various reasons such as budget constraints and privacy concerns, labels are very limited in many real-world scenarios. Directly applying standard representation learning approaches on small labeled data sets will easily run into over-fitting problems and lead to sub-optimal solutions. Even worse, in some domains such as education, the limited labels are usually annotated by multiple workers with diverse expertise, which yields noises and inconsistency in such crowdsourcing settings. In this paper, we propose a novel framework which aims to learn effective representations from limited data with crowdsourced labels. Specifically, we design a grouping based deep neural network to learn embeddings from a limited number of training samples and present a Bayesian confidence estimator to capture the inconsistency among crowdsourced labels. Furthermore, to expedite the training process, we develop a hard example selection procedure to adaptively pick up training examples that are misclassified by the model. Extensive experiments conducted on three real-world data sets demonstrate the superiority of our framework on learning representations from limited data with crowdsourced labels, comparing with various state-of-the-art baselines. In addition, we provide a comprehensive analysis on each of the main components of our proposed framework and also introduce the promising results it achieved in our real production to fully understand the proposed framework., Comment: IEEE Transactions on Knowledge and Data Engineering (Accepted)

Asking questions is one of the most crucial pedagogical techniques used by teachers in class. It not only offers open-ended discussions between teachers and students to exchange ideas but also provokes deeper student thought and critical analysis. Providing teachers with such pedagogical feedback will remarkably help teachers improve their overall teaching quality over time in classrooms. Therefore, in this work, we build an end-to-end neural framework that automatically detects questions from teachers’ audio recordings. Compared with traditional methods, our approach not only avoids cumbersome feature engineering, but also adapts to the task of multi-class question detection in real education scenarios. By incorporating multi-task learning techniques, we are able to strengthen the understanding of semantic relations among different types of questions. We conducted extensive experiments on the question detection tasks in a real-world online classroom dataset and the results demonstrate the superiority of our model in terms of various evaluation metrics.

Items in real-world recommender systems exhibit certain hierarchical structures. Similarly, user preferences also present hierarchical structures. Recent studies show that incorporating the hierarchy of items or user preferences can improve the performance of recommender systems. However, hierarchical structures are often not explicitly available, especially those of user preferences. Thus, there's a gap between the importance of hierarchies and their availability. In this paper, we investigate the problem of exploring the implicit hierarchical structures for recommender systems when they are not explicitly available. We propose a novel recommendation framework to bridge the gap, which enables us to explore the implicit hierarchies of users and items simultaneously. We then extend the framework to integrate explicit hierarchies when they are available, which gives a unified framework for both explicit and implicit hierarchical structures. Experimental results on real-world datasets demonstrate the effectiveness of the proposed framework by incorporating implicit and explicit structures.

Social media provides a platform for seeking information from a large user base. Information seeking in social media, however, occurs simultaneously with users expressing their viewpoints by making statements. Rhetorical questions have the form of a question but serve the function of a statement and are an important tool employed by users to express their viewpoints. Therefore, rhetorical questions might mislead platforms assisting information seeking in social media. It becomes difficult to identify rhetorical questions as they are not syntactically different from other questions. In this article, we develop a framework to identify rhetorical questions by modeling some motivations of the users to post them. We focus on two motivations of the users drawing from linguistic theories to implicitly convey a message and to modify the strength of a statement previously made. We develop a quantitative framework from these motivations to identify rhetorical questions in social media. We evaluate the framework using two datasets of questions posted on a social media platform Twitter and demonstrate its effectiveness in identifying rhetorical questions. This is the first framework, to the best of our knowledge, to model the possible motivations for posting rhetorical questions to identify them on social media platforms.

The fast development of cloud technology has brought about a new trend in the field of information service: more and more information is being transferred to the cloud as requested. However, the data, such as texts, images, sounds, and videos, before being moved to the cloud, in most cases, has to be encrypted so that intelligible information will not be obtained from unauthorized accesses. While having done a nice work in protecting the data privacy of its owners, this encrypting process, has produced a great challenge for retrieval of the document stored via traditional IR model based on document, query and relevance. In order to retrieve encrypted information from cloud, an alternative retrieval system is needed. To satisfy such a need, we have: 1) build a cloud information retrieval framework characterized by its retrieval risk formula, which, enables, for the very first time to the best of our knowledge, an effective retrieval of keywords from encrypted cloud data without undermining key word privacy and retrieval performance; and 2) upgraded the existing searchable encryption scheme that can only support simple equality queries on encrypted data and has been proved to perform slightly better than random selection, so that it can now support the state-of-art information retrieval methods, such as vector space, probabilistic, and language model. To evaluate the effect of the system proposed above, we've conducted a wide range of experiments on benchmark data sets, of which the results shows that solution can fulfill its purposes quite well in various settings.

Social media plays a major role in helping people affected by natural calamities. These people use social media to request information and help in situations where time is a critical commodity. However, generic social media platforms like Twitter and Facebook are not conducive for obtaining answers promptly. Algorithms to ensure prompt responders for questions in social media have to understand and model the factors affecting their response time. In this paper, we draw from sociological studies on information seeking and organizational behavior to identify users who can provide timely and relevant responses to questions posted on social media. We first draw from these theories to model the future availability and past response behavior of the candidate responders and integrate these criteria with user relevance. We propose a learning algorithm from these criteria to derive optimal rankings of responders for a given question. We present questions posted on Twitter as a form of information seeking activity in social media and use them to evaluate our framework. Our experiments demonstrate that the proposed framework is useful in identifying timely and relevant responders for questions in social media.

Location information of Web pages plays an important role in location-sensitive tasks such as Web search ranking for location-sensitive queries. However, such information is usually ambiguous, incomplete, or even missing, which raises the problem of location prediction for Web pages. Meanwhile, Web pages are massive and often noisy, which pose challenges to the majority of existing algorithms for location prediction. In this paper, we propose a novel and scalable location prediction framework for Web pages based on the query-URL click graph. In particular, we introduce a concept of term location vectors to capture location distributions for all terms and develop an automatic approach to learn the importance of each term location vector for location prediction. Empirical results on a large URL set demonstrate that the proposed framework significantly improves the location prediction accuracy comparing with various representative baselines. We further provide a principled way to incorporate the proposed framework into the search ranking task and experimental results on a commercial search engine show that the proposed method remarkably boosts the ranking performance for location-sensitive queries.

Word embedding has been proven to be a useful model for various natural language processing tasks. Traditional word embedding methods merely take into account word distributions independently from any specific tasks. Hence, the resulting representations could be sub-optimal for a given task. In the context of sentiment analysis, there are various types of prior knowledge available, e.g., sentiment labels of documents from available datasets or polarity values of words from sentiment lexicons. We incorporate such prior sentiment information at both word level and document level in order to investigate the influence each word has on the sentiment label of both target word and context words. By evaluating the performance of sentiment analysis in each category, we find the best way of incorporating prior sentiment information. Experimental results on real-world datasets demonstrate that the word representations learnt by DLJT2 can significantly improve the sentiment analysis performance. We prove that incorporating prior sentiment knowledge into the embedding process has the potential to learn better representations for sentiment analysis.

The increasing popularity and diversity of social media sites has encouraged more and more people to participate on multiple online social networks to enjoy their services. Each user may create a user identity, which can includes profile, content, or network information, to represent his or her unique public figure in every social network. Thus, a fundamental question arises -- can we link user identities across online social networks? User identity linkage across online social networks is an emerging task in social media and has attracted increasing attention in recent years. Advancements in user identity linkage could potentially impact various domains such as recommendation and link prediction. Due to the unique characteristics of social network data, this problem faces tremendous challenges. To tackle these challenges, recent approaches generally consist of (1) extracting features and (2) constructing predictive models from a variety of perspectives. In this paper, we review key achievements of user identity linkage across online social networks including stateof- the-art algorithms, evaluation metrics, and representative datasets. We also discuss related research areas, open problems, and future research directions for user identity linkage across online social networks.

Robust language processing systems are becoming increasingly important given the recent awareness of dangerous situations where brittle machine learning models can be easily broken with the presence of noises. In this paper, we introduce a robust word recognition framework that captures multi-level sequential dependencies in noised sentences. The proposed framework employs a sequence-to-sequence model over characters of each word, whose output is given to a word-level bi-directional recurrent neural network. We conduct extensive experiments to verify the effectiveness of the framework. The results show that the proposed framework outperforms state-of-the-art methods by a large margin and they also suggest that character-level dependencies can play an important role in word recognition. The code of the proposed framework and the major experiments are publicly available1.

A large portion of today's big data can be represented as networks. However, not all networks are the same, and in fact, for many that have additional complexities to their structure, traditional general network analysis methods are no longer applicable. For example, signed networks contain both positive and negative links, and thus dedicated theories and algorithms have been developed. However, previous work mainly focuses on the unipartite setting where signed links connect any pair of nodes. Signed bipartite networks on the one hand, are commonly found, but have primarily been overlooked. Their complexities of having two node types where signed links can only form across the two sets introduce challenges that prevent most existing literature on unipartite signed and unsigned bipartite networks from being applied. On the other hand, balance theory, a key signed social theory, has been generally defined for cycles of any length and is being used in the form of triangles for numerous unipartite signed network tasks. However, in bipartite networks there are no triangles and furthermore there exist two types of nodes. Therefore, in this work, we conduct the first comprehensive analysis and validation of balance theory using the smallest cycle in signed bipartite networks - signed butterflies (i.e., cycles of length 4 containing the two node types). Then, to investigate the applicability of balance theory aiding signed bipartite network tasks, we develop multiple sign prediction methods that utilize balance theory in the form of signed butterflies. Our sign prediction experiment on three real-world signed bipartite networks demonstrates the effectiveness of using these signed butterflies for not only sign prediction, but paves the way for improvements in other signed bipartite network analysis tasks., Comment: CIKM 2019

In recent times we have seen a trend of having the ideologies of the two dominant political parties in the U.S. growing further and further apart. Simultaneously we have entered the age of big data raising enormous interest in computational approaches to solve problems in many domains such as political elections. However, an overlooked problem lies in predicting what happens once our elected officials take office, more specifically, predicting the congressional votes, which are perhaps the most influential decisions being made in the U.S. This, nevertheless, is far from a trivial task, since the congressional system is highly complex and heavily influenced by both ideological and social factors. Thus, dedicated efforts are required to first effectively identify and represent these factors, then furthermore capture the interactions between them. To this end, we proposed a robust end-to-end framework Multi-Factor Congressional Vote Prediction (MFCVP) that defines and encodes features from indicative ideological factors while also extracting novel social features. This allows for a principled expressive representation of the complex system, which ultimately leads to MFCVP making accurate vote predictions. Experimental results on a dataset from the U.S. House of Representatives shows the superiority of MFCVP to several representatives approaches when predicting votes for individual representatives and also the overall outcome of the bill voted on. Finally, we perform a factor analysis to understand the effectiveness and interplay between the different factors.

Recent years have witnessed rapid developments on social recommendation techniques for improving the performance of recommender systems due to the growing influence of social networks to our daily life. The majority of existing social recommendation methods unify user representation for the user-item interactions (item domain) and user-user connections (social domain). However, it may restrain user representation learning in each respective domain, since users behave and interact differently in the two domains, which makes their representations to be heterogeneous. In addition, most of traditional recommender systems can not efficiently optimize these objectives, since they utilize negative sampling technique which is unable to provide enough informative guidance towards the training during the optimization process. In this paper, to address the aforementioned challenges, we propose a novel deep adversarial social recommendation framework DASO. It adopts a bidirectional mapping method to transfer users' information between social domain and item domain using adversarial learning. Comprehensive experiments on two real-world datasets show the effectiveness of the proposed framework., Accepted by International Joint Conference on Artificial Intelligence (IJCAI 2019)

Learning representation has been proven to be helpful in numerous machine learning tasks. The success of the majority of existing representation learning approaches often requires a large amount of consistent and noise-free labels. However, labels are not accessible in many real-world scenarios and they are usually annotated by the crowds. In practice, the crowdsourced labels are usually inconsistent among crowd workers given their diverse expertise and the number of crowdsourced labels is very limited. Thus, directly adopting crowdsourced labels for existing representation learning algorithms is inappropriate and suboptimal. In this paper, we investigate the above problem and propose a novel framework of \textbf{R}epresentation \textbf{L}earning with crowdsourced \textbf{L}abels, i.e., "RLL", which learns representation of data with crowdsourced labels by jointly and coherently solving the challenges introduced by limited and inconsistent labels. The proposed representation learning framework is evaluated in two real-world education applications. The experimental results demonstrate the benefits of our approach on learning representation from limited labeled data from the crowds, and show RLL is able to outperform state-of-the-art baselines. Moreover, detailed experiments are conducted on RLL to fully understand its key components and the corresponding performance.

Recommender systems are crucial to alleviate the information overload problem in online worlds. Most of the modern recommender systems capture users' preference towards items via their interactions based on collaborative filtering techniques. In addition to the user-item interactions, social networks can also provide useful information to understand users' preference as suggested by the social theories such as homophily and influence. Recently, deep neural networks have been utilized for social recommendations, which facilitate both the user-item interactions and the social network information. However, most of these models cannot take full advantage of the social network information. They only use information from direct neighbors, but distant neighbors can also provide helpful information. Meanwhile, most of these models treat neighbors' information equally without considering the specific recommendations. However, for a specific recommendation case, the information relevant to the specific item would be helpful. Besides, most of these models do not explicitly capture the neighbor's opinions to items for social recommendations, while different opinions could affect the user differently. In this paper, to address the aforementioned challenges, we propose DSCF, a Deep Social Collaborative Filtering framework, which can exploit the social relations with various aspects for recommender systems. Comprehensive experiments on two-real world datasets show the effectiveness of the proposed framework., Accepted by 13th ACM Conference on Recommender Systems (RecSys 2019, Long Paper)

To employ millimeter wave technology in the 5G standard, two inherent challenges need to be addressed in dynamic outdoor environments. Firstly, different types of obstacles can easily block the links. Secondly, the link quality can drop significantly in a mobile environment. It is critical to discriminate between the two different situations to take appropriate actions. The existing work to make the distinction is based on RSSI variation measured in a time window, which is very time-consuming leading to large volume of data loss in order to achieve high accuracy. In this paper, we propose a learning-based prediction framework to classify link blockage and link movement efficiently and quickly. A classifier is trained with data blockage instances using different learning methods and is used to make a prediction based on diffraction values on different multipath components formed around a receiver. The simulations show that the prediction framework can predict blockage with close to 90% accuracy. The prediction framework will eliminate the need for having time-consuming methods to discriminate between link movement and link blockage. Experiments show that our framework does not need large amount of training data to get to the desired prediction accuracy.

Mobile applications for weight loss are becoming increasingly popular due to their cost-effective and wide-reaching characteristics. The self-monitoring function in these applications plays a crucial role in gaining success of weight loss intervention, as it can give tailored feedback and motivation enhancement to users. Thus, by shortening such self-reinforcement cycle and providing timely feedback at much earlier stage, precisely predicting user’s future weight will significantly improve the effectiveness of existing applications. In this paper, we investigate the weight loss prediction problem by leveraging social-temporal information, which is abundant and ubiquitous in weight loss applications. The study is based on a large-scale dataset from a weight loss application BOOHEE, which contains more than 9 million users with a timespan of multiple years (from 2012 to 2015). Our analysis validates the existence of social-temporal correlations in weight loss and modeling these correlations leads to a novel weight LOss prediction framework in Social-Temporal context LOST. The experimental results on the real-world dataset demonstrate the effectiveness of the proposed framework. Further experiments have been conducted to understand the importance of social-temporal correlations in weight loss prediction.

In modern recommender systems, both users and items are associated with rich side information, which can help understand users and items. Such information is typically heterogeneous and can be roughly categorized into flat and hierarchical side information. While side information has been proved to be valuable, the majority of existing systems have exploited either only flat side information or only hierarchical side information due to the challenges brought by the heterogeneity. In this paper, we investigate the problem of exploiting heterogeneous side information for recommendations. Specifically, we propose a novel framework jointly captures flat and hierarchical side information with mathematical coherence. We demonstrate the effectiveness of the proposed framework via extensive experiments on various real-world datasets. Empirical results show that our approach is able to lead a significant performance gain over the state-of-the-art methods.

Convolutional neural networks (CNNs) leverage the great power in representation learning on regular grid data such as image and video. Recently, increasing attention has been paid on generalizing CNNs to graph or network data which is highly irregular. Some focus on graph-level representation learning while others aim to learn node-level representations. These methods have been shown to boost the performance of many graph-level tasks such as graph classification and node-level tasks such as node classification. Most of these methods have been designed for single-dimensional graphs where a pair of nodes can only be connected by one type of relation. However, many real-world graphs have multiple types of relations and they can be naturally modeled as multi-dimensional graphs with each type of relation as a dimension. Multi-dimensional graphs bring about richer interactions between dimensions, which poses tremendous challenges to the graph convolutional neural networks designed for single-dimensional graphs. In this paper, we study the problem of graph convolutional networks for multi-dimensional graphs and propose a multi-dimensional convolutional neural network model mGCN aiming to capture rich information in learning node-level representations for multi-dimensional graphs. Comprehensive experiments on real-world multi-dimensional graphs demonstrate the effectiveness of the proposed framework.

On the one hand, nowadays, fake news articles are easily propagated through various online media platforms and have become a grand threat to the trustworthiness of information. On the other hand, our understanding of the language of fake news is still minimal. Incorporating hierarchical discourse-level structure of fake and real news articles is one crucial step toward a better understanding of how these articles are structured. Nevertheless, this has rarely been investigated in the fake news detection domain and faces tremendous challenges. First, existing methods for capturing discourse-level structure rely on annotated corpora which are not available for fake news datasets. Second, how to extract out useful information from such discovered structures is another challenge. To address these challenges, we propose Hierarchical Discourse-level Structure for Fake news detection. HDSF learns and constructs a discourse-level structure for fake/real news articles in an automated and data-driven manner. Moreover, we identify insightful structure-related properties, which can explain the discovered structures and boost our understating of fake news. Conducted experiments show the effectiveness of the proposed approach. Further structural analysis suggests that real and fake news present substantial differences in the hierarchical discourse-level structures., Accepted to 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics June 2-7, 2019 Minneapolis, USA

With the recent prevalence of Reinforcement Learning (RL), there have been tremendous interests in developing RL-based recommender systems. In practical recommendation sessions, users will sequentially access multiple scenarios, such as the entrance pages and the item detail pages, and each scenario has its specific characteristics. However, the majority of existing RL-based recommender systems focus on optimizing one strategy for all scenarios or separately optimizing each strategy, which could lead to sub-optimal overall performance. In this paper, we study the recommendation problem with multiple (consecutive) scenarios, i.e., whole-chain recommendations. We propose a multi-agent RL-based approach (DeepChain), which can capture the sequential correlation among different scenarios and jointly optimize multiple recommendation strategies. To be specific, all recommender agents (RAs) share the same memory of users' historical behaviors, and they work collaboratively to maximize the overall reward of a session. Note that optimizing multiple recommendation strategies jointly faces two challenges in the existing model-free RL model - (i) it requires huge amounts of user behavior data, and (ii) the distribution of reward (users' feedback) are extremely unbalanced. In this paper, we introduce model-based RL techniques to reduce the training data requirement and execute more accurate strategy updates. The experimental results based on a real e-commerce platform demonstrate the effectiveness of the proposed framework., 29th ACM International Conference on Information and Knowledge Management

The failure of landing a job for college students could cause serious social consequences such as drunkenness and suicide. In addition to academic performance, unconscious biases can become one key obstacle for hunting jobs for graduating students. Thus, it is necessary to understand these unconscious biases so that we can help these students at an early stage with more personalized intervention. In this paper, we develop a framework, i.e., MAYA (Multi-mAjor emploYment stAtus) to predict students' employment status while considering biases. The framework consists of four major components. Firstly, we solve the heterogeneity of student courses by embedding academic performance into a unified space. Then, we apply a generative adversarial network (GAN) to overcome the class imbalance problem. Thirdly, we adopt Long Short-Term Memory (LSTM) with a novel dropout mechanism to comprehensively capture sequential information among semesters. Finally, we design a bias-based regularization to capture the job market biases. We conduct extensive experiments on a large-scale educational dataset and the results demonstrate the effectiveness of our prediction framework.

Graph neural networks, which generalize deep neural network models to graph structured data, have attracted increasing attention in recent years. They usually learn node representations by transforming, propagating and aggregating node features and have been proven to improve the performance of many graph related tasks such as node classification and link prediction. To apply graph neural networks for the graph classification task, approaches to generate the \textit{graph representation} from node representations are demanded. A common way is to globally combine the node representations. However, rich structural information is overlooked. Thus a hierarchical pooling procedure is desired to preserve the graph structure during the graph representation learning. There are some recent works on hierarchically learning graph representation analogous to the pooling step in conventional convolutional neural (CNN) networks. However, the local structural information is still largely neglected during the pooling process. In this paper, we introduce a pooling operator $\pooling$ based on graph Fourier transform, which can utilize the node features and local structures during the pooling process. We then design pooling layers based on the pooling operator, which are further combined with traditional GCN convolutional layers to form a graph neural network framework $\m$ for graph classification. Theoretical analysis is provided to understand $\pooling$ from both local and global perspectives. Experimental results of the graph classification task on $6$ commonly used benchmarks demonstrate the effectiveness of the proposed framework.

Monitoring student knowledge states or skill acquisition levels known as knowledge tracing, is a fundamental part of intelligent tutoring systems. Despite its inherent challenges, recent deep neural networks based knowledge tracing models have achieved great success, which is largely from models’ ability to learn sequential dependencies of questions in student exercise data. However, in addition to sequential information, questions inherently exhibit side relations, which can enrich our understandings about student knowledge states and has great potentials to advance knowledge tracing. Thus, in this paper, we exploit side relations to improve knowledge tracing and design a novel framework DTKS. The experimental results on real education data validate the effectiveness of the proposed framework and demonstrate the importance of side information in knowledge tracing.

Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised concerns about applying deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types, such as images, graphs and text. Thus, it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures. In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for the three popular data types, i.e., images, graphs and text., Comment: survey, adversarial attacks, defenses

Recently there are increasing concerns about the fairness of Artificial Intelligence (AI) in real-world applications such as computer vision and recommendations. For example, recognition algorithms in computer vision are unfair to black people such as poorly detecting their faces and inappropriately identifying them as "gorillas". As one crucial application of AI, dialogue systems have been extensively applied in our society. They are usually built with real human conversational data; thus they could inherit some fairness issues which are held in the real world. However, the fairness of dialogue systems has not been well investigated. In this paper, we perform a pioneering study about the fairness issues in dialogue systems. In particular, we construct a benchmark dataset and propose quantitative measures to understand fairness in dialogue models. Our studies demonstrate that popular dialogue models show significant prejudice towards different genders and races. Besides, to mitigate the bias in dialogue systems, we propose two simple but effective debiasing methods. Experiments show that our methods can reduce the bias in dialogue systems significantly. The dataset and the implementation are released to foster fairness research in dialogue systems., Comment: Accepted by COLING 2020

Automatic short answer grading (ASAG), which autonomously score student answers according to reference answers, provides a cost-effective and consistent approach to teaching professionals and can reduce their monotonous and tedious grading workloads. However, ASAG is a very challenging task due to two reasons: (1) student answers are made up of free text which requires a deep semantic understanding; and (2) the questions are usually open-ended and across many domains in K-12 scenarios. In this paper, we propose a generalized end-to-end ASAG learning framework which aims to (1) autonomously extract linguistic information from both student and reference answers; and (2) accurately model the semantic relations between free-text student and reference answers in open-ended domain. The proposed ASAG model is evaluated on a large real-world K-12 dataset and can outperform the state-of-the-art baselines in terms of various evaluation metrics.

There are various real-world applications such as video ads, airport screenings, courtroom trials, and job interviews where deception detection can play a crucial role. Hence, there are immense demands on deception detection in videos. However, videos are inherently complex; moreover, they lack detective labels in many real-world applications, which poses tremendous challenges to traditional deception detection methods. In this paper, we study the problem of deception detection in videos. In particular, we provide a principled way to capture rich information into a coherent model and propose an end-to-end framework DEV to detect DEceptive Videos automatically, which is robust to the small number of training data. Experimental results on real-world videos demonstrate the effectiveness of the proposed framework and further experiments are conducted to understand important factors of deception detection in videos.

Big data is ubiquitous and can only become bigger, which challenges traditional data mining and machine learning methods. Social media is a new source of data that is significantly different from conventional ones. Social media data are mostly user-generated, and are big, linked, and heterogeneous. We present the good, the bad and the ugly associated with the multi-faceted social media data and exemplify the importance of some original problems with real-world examples. We discuss bias in social media data, evaluation dilemma, data reduction, inferring invisible information, and big-data paradox. We illuminate new opportunities of developing novel algorithms and tools for data science. In our endeavor of employing the good to tame the bad with the help of the ugly, we deepen the understanding of ever growing and continuously evolving data and create innovative solutions with interdisciplinary and collaborative research of data science.

A novel compressive sensing based multi-document summarization with group sparse learning (SGS) framework is proposed.Sentences in documents are considered as a kind of sparse or compressible signals.We jointly select summary sentences with the learnt group structure pattern to discriminate the important and the redundant information simultaneously.An accelerated projection gradient algorithm is developed to solve the group sparse convex optimization problem of the proposed framework efficiently.Experimental results on DUC 2006 and TAC 2007 main task corpus demonstrate the effectiveness of our proposed framework. Multi-document summarization (MDS) aims to capture the core information from a set of topic-specific documents. Most existing extractive methods evaluate sentences individually and select summary sentences one by one, which may ignore the hidden structure patterns among sentences and fail to keep less redundancy from the global perspective. We study this task from the perspective of compressive sensing, consider sentences in documents as a kind of signals, which are usually sparse or compressible in the sense that they have concise representation pattern expressed in the proper sentence basis and transform it to a group sparse representation issue. A novel multi-document Summarization with Group Sparse learning (SGS) framework is proposed, which can maximally reconstruct the original documents via minimizing the approximation error and jointly select summary sentences with the learnt group structure information among sentences. The summary relatedness can be modeled by constraining the reconstruction models to be close to each other, and make multiple sentences share a common underlying structure to form the summary content. With this model, we take the global information into account in evaluating the importance of sentences and further reduce the redundancy. In order to solve this group sparse convex optimization problem for MDS, we also develop an efficient algorithm based on the Nesterov's method, which leads to much faster convergence rate than some traditional methods. Experimental results on DUC 2006 and TAC 2007 main task corpora show the effectiveness of our proposed framework. The relevant experiments are conducted to demonstrate the working mechanism of main components in the SGS framework.

Due to the fact much of today's data can be represented as graphs, there has been a demand for generalizing neural network models for graph data. One recent direction that has shown fruitful results, and therefore growing interest, is the usage of graph convolutional neural networks (GCNs). They have been shown to provide a significant improvement on a wide range of tasks in network analysis, one of which being node representation learning. The task of learning low-dimensional node representations has shown to increase performance on a plethora of other tasks from link prediction and node classification, to community detection and visualization. Simultaneously, signed networks (or graphs having both positive and negative links) have become ubiquitous with the growing popularity of social media. However, since previous GCN models have primarily focused on unsigned networks (or graphs consisting of only positive links), it is unclear how they could be applied to signed networks due to the challenges presented by negative links. The primary challenges are based on negative links having not only a different semantic meaning as compared to positive links, but their principles are inherently different and they form complex relations with positive links. Therefore we propose a dedicated and principled effort that utilizes balance theory to correctly aggregate and propagate the information across layers of a signed GCN model. We perform empirical experiments comparing our proposed signed GCN against state-of-the-art baselines for learning node representations in signed networks. More specifically, our experiments are performed on four real-world datasets for the classical link sign prediction problem that is commonly used as the benchmark for signed network embeddings algorithms.

Dimensionality reduction techniques can be categorized mainly into feature extraction and feature selection. In the feature extraction approach, features are projected into a new space with lower dimensionality. Feature selection is broadly categorized into four models: filter model, wrapper model, embedded model, and hybrid model. With the existence of a large number of features, learning models tend to overfit and their learning performance degenerates. Feature selection is one of the most used techniques to reduce dimensionality among practitioners. The existence of irrelevant features in the data set may degrade learning quality and consume more memory and computational time that could be saved if these features were removed. However, finding clusters in high-dimensional space is computationally expensive and may degrade the learning performance. Clustering is useful in several machine learning and data mining tasks including image segmentation, information retrieval, pattern recognition, pattern classification, and network analysis.