Search

Currently, many intelligence systems contain the texts from multi-sources, e.g., bulletin board system (BBS) posts, tweets and news. These texts can be ``comparative'' since they may be semantically correlated and thus provide us with different perspectives toward the same topics or events. To better organize the multi-sourced texts and obtain more comprehensive knowledge, we propose to study the novel problem of Mutual Clustering on Comparative Texts (MCCT), which aims to cluster the comparative texts simultaneously and collaboratively. The MCCT problem is difficult to address because 1) comparative texts usually present different data formats and structures and thus they are hard to organize, and 2) there lacks an effective method to connect the semantically correlated comparative texts to facilitate clustering them in an unified way. To this aim, in this paper we propose a Heterogeneous Information Network-based Text clustering framework HINT. HINT first models multi-sourced texts (e.g. news and tweets) as heterogeneous information networks by introducing the shared ``anchor texts'' to connect the comparative texts. Next, two similarity matrices based on HINT as well as a transition matrix for cross-text-source knowledge transfer are constructed. Comparative texts clustering are then conducted by utilizing the constructed matrices. Finally, a mutual clustering algorithm is also proposed to further unify the separate clustering results of the comparative texts by introducing a clustering consistency constraint. We conduct extensive experimental on three tweets-news datasets, and the results demonstrate the effectiveness and robustness of the proposed method in addressing the MCCT problem.

Network embedding, as a promising way of the network representation learning, is capable of supporting various subsequent network mining and analysis tasks, and has attracted growing research interests recently. Traditional approaches assign each node with an independent continuous vector, which will cause huge memory overhead for large networks. In this paper we propose a novel multi-hot compact embedding strategy to effectively reduce memory cost by learning partially shared embeddings. The insight is that a node embedding vector is composed of several basis vectors, which can significantly reduce the number of continuous vectors while maintain similar data representation ability. Specifically, we propose a MCNE model to learn compact embeddings from pre-learned node features. A novel component named compressor is integrated into MCNE to tackle the challenge that popular back-propagation optimization cannot propagate through discrete samples. We further propose an end-to-end model MCNE$_{t}$ to learn compact embeddings from the input network directly. Empirically, we evaluate the proposed models over three real network datasets, and the results demonstrate that our proposals can save about 90\% of memory cost of network embeddings without significantly performance decline.

Recently deep learning based Natural Language Processing (NLP) models have shown great potential in the modeling of source code. However, a major limitation of these approaches is that they take source code as simple tokens of text and ignore its contextual, syntactical and structural dependencies. In this work, we present CodeGRU, a gated recurrent unit based source code language model that is capable of capturing source code's contextual, syntactical and structural dependencies. We introduce a novel approach which can capture the source code context by leveraging the source code token types. Further, we adopt a novel approach which can learn variable size context by taking into account source code's syntax, and structural information. We evaluate CodeGRU with real-world data set and it shows that CodeGRU outperforms the state-of-the-art language models and help reduce the vocabulary size up to 24.93\%. Unlike previous works, we tested CodeGRU with an independent test set which suggests that our methodology does not requisite the source code comes from the same domain as training data while providing suggestions. We further evaluate CodeGRU with two software engineering applications: source code suggestion, and source code completion. Our experiment confirms that the source code's contextual information can be vital and can help improve the software language models. The extensive evaluation of CodeGRU shows that it outperforms the state-of-the-art models. The results further suggest that the proposed approach can help reduce the vocabulary size and is of practical use for software developers.

Many real-world problems can be represented as graph-based learning problems. In this paper, we propose a novel framework for learning spatial and attentional convolution neural networks on arbitrary graphs. Different from previous convolutional neural networks on graphs, we first design a motif-matching guided subgraph normalization method to capture neighborhood information. Then we implement subgraph-level self-attentional layers to learn different importances from different subgraphs to solve graph classification problems. Analogous to image-based attentional convolution networks that operate on locally connected and weighted regions of the input, we also extend graph normalization from one-dimensional node sequence to two-dimensional node grid by leveraging motif-matching, and design self-attentional layers without requiring any kinds of cost depending on prior knowledge of the graph structure. Our results on both bioinformatics and social network datasets show that we can significantly improve graph classification benchmarks over traditional graph kernel and existing deep models.

Traditional stock market prediction methods commonly only utilize the historical trading data, ignoring the fact that stock market fluctuations can be impacted by various other information sources such as stock related events. Although some recent works propose event-driven prediction approaches by considering the event data, how to leverage the joint impacts of multiple data sources still remains an open research problem. In this work, we study how to explore multiple data sources to improve the performance of the stock prediction. We introduce an Extended Coupled Hidden Markov Model incorporating the news events with the historical trading data. To address the data sparsity issue of news events for each single stock, we further study the fluctuation correlations between the stocks and incorporate the correlations into the model to facilitate the prediction task. Evaluations on China A-share market data in 2016 show the superior performance of our model against previous methods., Comment: 19 pages

Collaborative Filtering (CF) is a widely adopted technique in recommender systems. Traditional CF models mainly focus on predicting a user's preference to the items in a single domain such as the movie domain or the music domain. A major challenge for such models is the data sparsity problem, and especially, CF cannot make accurate predictions for the cold-start users who have no ratings at all. Although Cross-Domain Collaborative Filtering (CDCF) is proposed for effectively transferring users' rating preference across different domains, it is still difficult for existing CDCF models to tackle the cold-start users in the target domain due to the extreme data sparsity. In this paper, we propose a Cross-Domain Latent Feature Mapping (CDLFM) model for cold-start users in the target domain. Firstly, in order to better characterize users in sparse domains, we take the users' similarity relationship on rating behaviors into consideration and propose the Matrix Factorization by incorporating User Similarities (MFUS) in which three similarity measures are proposed. Next, to perform knowledge transfer across domains, we propose a neighborhood based gradient boosting trees method to learn the cross-domain user latent feature mapping function. For each cold-start user, we learn his/her feature mapping function based on the latent feature pairs of those linked users who have similar rating behaviors with the cold-start user in the auxiliary domain. And the preference of the cold-start user in the target domain can be predicted based on the mapping function and his/her latent features in the auxiliary domain. Experimental results on two real data sets extracted from Amazon transaction data demonstrate the superiority of our proposed model against other state-of-the-art methods., Comment: 16 pages, 8 figures

Relation extraction has been widely studied to extract new relational facts from open corpus. Previous relation extraction methods are faced with the problem of wrong labels and noisy data, which substantially decrease the performance of the model. In this paper, we propose an ensemble neural network model - Adaptive Boosting LSTMs with Attention, to more effectively perform relation extraction. Specifically, our model first employs the recursive neural network LSTMs to embed each sentence. Then we import attention into LSTMs by considering that the words in a sentence do not contribute equally to the semantic meaning of the sentence. Next via adaptive boosting, we build strategically several such neural classifiers. By ensembling multiple such LSTM classifiers with adaptive boosting, we could build a more effective and robust joint ensemble neural networks based relation extractor. Experiment results on real dataset demonstrate the superior performance of the proposed model, improving F1-score by about 8% compared to the state-of-the-art models.

Traditional stock market prediction approaches commonly utilize the historical price-related data of the stocks to forecast their future trends. As the Web information grows, recently some works try to explore financial news to improve the prediction. Effective indicators, e.g., the events related to the stocks and the people's sentiments towards the market and stocks, have been proved to play important roles in the stocks' volatility, and are extracted to feed into the prediction models for improving the prediction accuracy. However, a major limitation of previous methods is that the indicators are obtained from only a single source whose reliability might be low, or from several data sources but their interactions and correlations among the multi-sourced data are largely ignored. In this work, we extract the events from Web news and the users' sentiments from social media, and investigate their joint impacts on the stock price movements via a coupled matrix and tensor factorization framework. Specifically, a tensor is firstly constructed to fuse heterogeneous data and capture the intrinsic relations among the events and the investors' sentiments. Due to the sparsity of the tensor, two auxiliary matrices, the stock quantitative feature matrix and the stock correlation matrix, are constructed and incorporated to assist the tensor decomposition. The intuition behind is that stocks that are highly correlated with each other tend to be affected by the same event. Thus, instead of conducting each stock prediction task separately and independently, we predict multiple correlated stocks simultaneously through their commonalities, which are enabled via sharing the collaboratively factorized low rank matrices between matrices and the tensor. Evaluations on the China A-share stock data and the HK stock data in the year 2015 demonstrate the effectiveness of the proposed model., Comment: Accepted by Knowledge-Based Systems

Traditional viral marketing problems aim at selecting a subset of seed users for one single product to maximize its awareness in social networks. However, in real scenarios, multiple products can be promoted in social networks at the same time. At the product level, the relationships among these products can be quite intertwined, e.g., competing, complementary and independent. In this paper, we will study the "interTwined Influence Maximization" (i.e., TIM) problem for one product that we target on in online social networks, where multiple other competing/complementary/independent products are being promoted simultaneously. The TIM problem is very challenging to solve due to (1) few existing models can handle the intertwined diffusion procedure of multiple products concurrently, and (2) optimal seed user selection for the target product may depend on other products' marketing strategies a lot. To address the TIM problem, a unified greedy framework TIER (interTwined Influence EstimatoR) is proposed in this paper. Extensive experiments conducted on four different types of real-world social networks demonstrate that TIER can outperform all the comparison methods with significant advantages in solving the TIM problem., Comment: 11 pages, 5 figures, Accepted by ASONAM 2016

To enjoy more social network services, users nowadays are usually involved in multiple online social networks simultaneously. The shared users between different networks are called anchor users, while the remaining unshared users are named as non-anchor users. Connections between accounts of anchor users in different networks are defined as anchor links and networks partially aligned by anchor links can be represented as partially aligned networks. In this paper, we want to predict anchor links between partially aligned social networks, which is formally defined as the partial network alignment problem. The partial network alignment problem is very difficult to solve because of the following two challenges: (1) the lack of general features for anchor links, and (2) the "one-to-one$_\le$" (one to at most one) constraint on anchor links. To address these two challenges, a new method PNA (Partial Network Aligner) is proposed in this paper. PNA (1) extracts a set of explicit anchor adjacency features and latent topological features for anchor links based on the anchor meta path concept and tensor decomposition techniques, and (2) utilizes the generic stable matching to identify the non-anchor users to prune the redundant anchor links attached to them. Extensive experiments conducted on two real-world partially aligned social networks demonstrate that PNA can solve the partial network alignment problem very well and outperform all the other comparison methods with significant advantages., Comment: 12 pages, 7 figures, short version is the invited paper of IEEE IRI '15

The vast amount of geo-tagged social images has attracted great attention in research of predicting location using the plentiful content of images, such as visual content and textual description. Most of the existing researches use the text-based or vision-based method to predict location. There still exists a problem: how to effectively exploit the correlation between different types of content as well as their geographical distributions for location prediction. In this paper, we propose to predict image location by learning the latent relation between geographical location and multiple types of image content. In particularly, we propose a geographical topic model GTMI (geographical topic model of social image) to integrate multiple types of image content as well as the geographical distributions, In GTMI, image topic is modeled on both text vocabulary and visual feature. Each region has its own distribution over topics and hence has its own language model and vision pattern. The location of a new image is estimated based on the joint probability of image content and similarity measure on topic distribution between images. Experiment results demonstrate the performance of location prediction based on GTMI., Comment: 8 pages

Nowadays, the message diffusion links among users or websites drive the development of countless innovative applications. However, in reality, it is easier for us to observe the timestamps when different nodes in the network react on a message, while the connections empowering the diffusion of the message remain hidden. This motivates recent extensive studies on the network inference problem: unveiling the edges from the records of messages disseminated through them. Existing solutions are computationally expensive, which motivates us to develop an efficient two-step general framework, Clustering Embedded Network Inference (CENI). CENI integrates clustering strategies to improve the efficiency of network inference. By clustering nodes directly on the timelines of messages, we propose two naive implementations of CENI: Infection-centric CENI and Cascade-centric CENI. Additionally, we point out the critical dimension problem of CENI: instead of one-dimensional timelines, we need to first project the nodes to an Euclidean space of certain dimension before clustering. A CENI adopting clustering method on the projected space can better preserve the structure hidden in the cascades, and generate more accurately inferred links. This insight sheds light on other related work attempting to discover or utilize the latent cluster structure in the disseminated messages. By addressing the critical dimension problem, we propose the third implementation of the CENI framework: Projection-based CENI. Through extensive experiments on two real datasets, we show that the three CENI models only need around 20% $\sim$ 50% of the running time of state-of-the-art methods. Moreover, the inferred edges of Projection-based CENI preserves or even outperforms the effectiveness of state-of-the-art methods., Comment: Full-length version of the paper with the same title published in ICWSM 2015

Researchers or students entering a emerging research area are particularly interested in what newly published papers will be most cited and which young researchers will become influential in the future, so that they can catch the most recent advances and find valuable research directions. However, predicting the future importance of scientific articles and authors is challenging due to the dynamic nature of literature networks and evolving research topics. Different from most previous studies aiming to rank the current importance of literatures and authors, we focus on \emph{ranking the future popularity of new publications and young researchers} by proposing a unified ranking model to combine various available information. Specifically, we first propose to extract two kinds of text features, words and words co-occurrence to characterize innovative papers and authors. Then, instead of using static and un-weighted graphs, we construct time-aware weighted graphs to distinguish the various importance of links established at different time. Finally, by leveraging both the constructed text features and graphs, we propose a mutual reinforcement ranking framework called \emph{MRFRank} to rank the future importance of papers and authors simultaneously. Experimental results on the ArnetMiner dataset show that the proposed approach significantly outperforms the baselines on the metric \emph{recommendation intensity}., Comment: 9 pages, Proceedings of the 2014 SIAM International Conference on Data Mining