Search

Since real-world objects and their interactions are often multi-modal and multi-typed, heterogeneous networks have been widely used as a more powerful, realistic, and generic superclass of traditional homogeneous networks (graphs). Meanwhile, representation learning (\aka~embedding) has recently been intensively studied and shown effective for various network mining and analytical tasks. In this work, we aim to provide a unified framework to deeply summarize and evaluate existing research on heterogeneous network embedding (HNE), which includes but goes beyond a normal survey. Since there has already been a broad body of HNE algorithms, as the first contribution of this work, we provide a generic paradigm for the systematic categorization and analysis over the merits of various existing HNE algorithms. Moreover, existing HNE algorithms, though mostly claimed generic, are often evaluated on different datasets. Understandable due to the application favor of HNE, such indirect comparisons largely hinder the proper attribution of improved task performance towards effective data preprocessing and novel technical design, especially considering the various ways possible to construct a heterogeneous network from real-world application data. Therefore, as the second contribution, we create four benchmark datasets with various properties regarding scale, structure, attribute/label availability, and \etc.~from different sources, towards handy and fair evaluations of HNE algorithms. As the third contribution, we carefully refactor and amend the implementations and create friendly interfaces for 13 popular HNE algorithms, and provide all-around comparisons among them over multiple tasks and experimental settings., Accepted by IEEE TKDE. All code and data available at https://github.com/yangji9181/HNE

The rapid development of modern communication technologies—in particular, (mobile) phone communications—has largely facilitated human social interactions and information exchange. However, the emergence of telemarketing frauds can significantly dissipate individual fortune and social wealth, resulting in a potential slow down or damage to economics. In this work, we propose to spot telemarketing frauds, with an emphasis on unveiling the “ precise fraud ” phenomenon and the strategies that are used by fraudsters to precisely select targets. To study this problem, we employ a one-month complete dataset of telecommunication metadata in Shanghai with 54 million users and 698 million call logs. Through our study, we find that user's information might have been seriously leaked, and fraudsters have a preference over the target user's age and activity in mobile network. We further propose a novel semi-supervised learning framework to distinguish fraudsters from non-fraudsters. Experimental results on a real-world data show that our approach outperforms several state-of-the-art algorithms in accuracy of detecting fraudsters (e.g., $+0.278$ + 0 . 278 in terms of F1 on average). We believe that our study can potentially inform policymaking for government and mobile service providers.

Community detection aims to partition network nodes into a set of clusters, such that nodes are more densely connected to each other within the same cluster than other clusters. For attributed networks, apart from the denseness requirement of topology structure, the attributes of nodes in the same community should also be homogeneous. Network embedding has been proved extremely useful in a variety of tasks, such as node classification, link prediction, and graph visualization, but few works dedicated to unsupervised embedding of node features specified for clustering task, which is vital for community detection and graph clustering. By post-processing with clustering algorithms like k -means, most existing network embedding methods can be applied to clustering tasks. However, the learned embeddings are not designed for clustering task, they only learn topological and attributed information of networks, and no clustering-oriented information is explored. In this article, we propose an algorithm named Network Embedding for node Clustering (NEC) to learn network embedding for node clustering in attributed graphs. Specifically, the presented work introduces a framework that simultaneously learns graph structure-based representations and clustering-oriented representations together. The framework consists of the following three modules: graph convolutional autoencoder module, soft modularity maximization module, and self-clustering module. Graph convolutional autoencoder module learns node embeddings based on topological structure and node attributes. We introduce soft modularity, which can be easily optimized using gradient descent algorithms, to exploit the community structure of networks. By integrating clustering loss and embedding loss, NEC can jointly optimize node cluster labels assignment and learn representations that keep local structure of network. This model can be effectively optimized using stochastic gradient algorithm. Empirical experiments on real-world networks and synthetic networks validate the feasibility and effectiveness of our algorithm on community detection task compared with network embedding based methods and traditional community detection methods.

Similarity measure is one of the fundamental task in heterogeneous information network (HIN) analysis. It has been applied to many areas, such as product recommendation, clustering, and Web search. Most of the existing metrics can provide personalized services for users by taking a meta-path or meta-structure as input. However, these metrics may highly depend on the user-specified meta-path or meta-structure. In addition, users must know how to select an appropriate meta-path or meta-structure. In this article, we propose a novel similarity measure in HINs, called Recurrent Meta-Structure (RecurMS)-based Similarity (RMSS). The RecurMS as a schematic structure in HINs provides a unified framework for integrating all of the meta-paths and meta-structures, and can be constructed automatically by means of repetitively traversing the network schema. In order to formalize the semantics, the RecurMS is decomposed into several recurrent meta-paths and recurrent meta-trees, and we then define the commuting matrices of the recurrent meta-paths and meta-trees. All of these commuting matrices are combined together according to different weights. We propose two kinds of weighting strategies to determine the weights. The first is called the local weighting strategy that depends on the sparsity of the commuting matrices, and the second is called the global weighting strategy that depends on the strength of the commuting matrices. As a result, RMSS is defined by means of the weighted summation of the commuting matrices. Note that RMSS can also provide personalized services for users by means of the weights of the recurrent meta-paths and meta-trees. Experimental evaluations show that the proposed RMSS is robust and outperforms the existing metrics in terms of ranking and clustering task.

Many large-scale knowledge bases simultaneously represent two views of knowledge graphs (KGs): an ontology view for abstract and commonsense concepts, and an instance view for specific entities that are instantiated from ontological concepts. Existing KG embedding models, however, merely focus on representing one of the two views alone. In this paper, we propose a novel two-view KG embedding model, JOIE, with the goal to produce better knowledge embedding and enable new applications that rely on multi-view knowledge. JOIE employs both cross-view and intra-view modeling that learn on multiple facets of the knowledge base. The cross-view association model is learned to bridge the embeddings of ontological concepts and their corresponding instance-view entities. The intra-view models are trained to capture the structured knowledge of instance and ontology views in separate embedding spaces, with a hierarchy-aware encoding technique enabled for ontologies with hierarchies. We explore multiple representation techniques for the two model components and investigate with nine variants of JOIE. Our model is trained on large-scale knowledge bases that consist of massive instances and their corresponding ontological concepts connected via a (small) set of cross-view links. Experimental results on public datasets show that the best variant of JOIE significantly outperforms previous models on instance-view triple prediction task as well as ontology population on ontologyview KG. In addition, our model successfully extends the use of KG embeddings to entity typing with promising performance., KDD-19

Collaborative Filtering (CF), as one of the most popular approaches, is widely employed in recommender systems but suffers from the cold-start problem, where interactions are very limited for new users in the system. To deal with this issue, previous work has largely focused on utilizing various auxiliary information such as user profiles and social relationships to infer user preferences. However, the auxiliary information is not always available due to reasons such as user privacy concerns, making the CF approaches have to count on the limited interactions. Moreover, real-world situations require both accurate and quick recommendations for newly arrived users dynamically. Therefore, it is of critical importance to enable fast learning for new users during the training time of CF models. In this paper, we present a novel learning paradigm, named MetaCF, to learn an accurate CF model that makes fast adaptation on new users with limited interactions. Inspired by meta-learning, MetaCF treats the fast adaptation on a new user as a task and aims to learn a suitable model for initializing the adaption. To pursue a well-generalized model, MetaCF is equipped with a Dynamic Subgraph Sampling that accounts for the dynamic arrival of new users by dynamically generating representative adaptation tasks for existing users. Moreover, to stabilize the adaption procedure that faces the shortage of training samples, MetaCF further optimizes the learning rates for adaption in a fine-grained manner. MetaCF is applicable to any differentiable CF-based models where we demonstrate it on two representative ones, FISM [1] and NGCF [2]. Extensive experiments on three datasets validate the effectiveness of the proposed framework, which significantly outperforms state-of-the-art baselines by a large margin in the cold-start scenario where user-item interactions are limited.

If one customer buys a tennis racket, what are the best 3 complementary products to purchase together? 3 tennis ball packs, 3 headbands, 3 overgrips, or 1 of each respectively? Complementary product recommendation (CPR), aiming at providing product suggestions that are often bought together to serve a joint demand, forms a pivotal component of e-commerce service, however, existing methods are far from optimal. Given one product, how to recommend its complementary products of different types is the key problem we tackle in this work. We first conduct an extensive analysis to correct the inaccurate assumptions adopted by existing work to show that co-purchased products are not always complementary and further propose a new strategy to generate clean distant supervision labels for CPR modeling. Moreover, to bridge in the gap from existing work that CPR does not only need relevance modeling but also requires diversity to fulfill the whole purchase demand, we develop a deep learning framework, P-Companion to explicitly model both relevance and diversity. More specifically, given one product with its product type, P-Companion first uses an encoder-decoder network to predict multiple complementary product types, then a transfer metric learning network is developed to project the embedding of query product to each predicted complementary product type subspace and further learn the complementary relationship based on the distant supervision labels within each subspace. The whole framework can be trained from end-to-end and robust to cold-start products attributed to a novel pretrained product embedding module named Product2Vec, based on graph attention networks. Extensive offline experiments show that P-Companion outperforms state-of-the-art baselines by 7.1% increase on the Hit@10 score with well-controlled diversity. Production-wise, we deploy P-Companion to provide online recommendations for over 200M products at Amazon and observe significant gains on product sales and profit.

The widespread of Coronavirus has led to a worldwide pandemic with a high mortality rate. Currently, the knowledge accumulated from different studies about this virus is very limited. Leveraging a wide-range of biological knowledge, such as gene ontology and protein-protein interaction (PPI) networks from other closely related species presents a vital approach to infer the molecular impact of a new species. In this paper, we propose the transferred multi-relational embedding model Bio-JOIE to capture the knowledge of gene ontology and PPI networks, which demonstrates superb capability in modeling the SARS-CoV-2-human protein interactions. Bio-JOIE jointly trains two model components. The knowledge model encodes the relational facts from the protein and GO domains into separated embedding spaces, using a hierarchy-aware encoding technique employed for the GO terms. On top of that, the transfer model learns a non-linear transformation to transfer the knowledge of PPIs and gene ontology annotations across their embedding spaces. By leveraging only structured knowledge, Bio-JOIE significantly outperforms existing state-of-the-art methods in PPI type prediction on multiple species. Furthermore, we also demonstrate the potential of leveraging the learned representations on clustering proteins with enzymatic function into enzyme commission families. Finally, we show that Bio-JOIE can accurately identify PPIs between the SARS-CoV-2 proteins and human proteins, providing valuable insights for advancing research on this new disease., ACM BCB 2020, Best Student Paper

Graph similarity search aims to find the most similar graphs to a query in a graph database in terms of a given proximity measure, say Graph Edit Distance (GED). It is a widely studied yet still challenging problem. Most of the studies are based on the pruning-verification framework, which first prunes non-promising graphs and then conducts verification on the small candidate set. Existing methods are capable of managing databases with thousands or tens of thousands of graphs, but fail to scale to even larger database, due to their exact pruning strategy. Inspired by the recent success of deep-learning-based semantic hashing in image and document retrieval, we propose a novel graph neural network (GNN) based semantic hashing, i.e. GHashing, for approximate pruning. We first train a GNN with ground-truth GED results so that it learns to generate embeddings and hash codes that preserve GED between graphs. Then a hash index is built to enable graph lookup in constant time. To answer a query, we use the hash codes and the continuous embeddings as two-level pruning to retrieve the most promising candidates, which are sent to the exact solver for final verification. Due to the approximate pruning strategy leveraged by our graph hashing technique, our approach achieves significantly faster query time compared to state-of-the-art methods while maintaining a high recall. Experiments show that our approach is on average 20x faster than the only baseline that works on million-scale databases, which demonstrates GHashing successfully provides a new direction in addressing graph search problem for large-scale graph databases.

Graph neural networks (GNNs) have received more and more attention in past several years, due to the wide applications of graphs and networks, and the superiority of their performance compared to traditional heuristics-driven approaches. However, most existing GNNs still focus on node-level applications, such as node classification and link prediction, and many challenging graph tasks are graph-level, such as graph search. In this talk, I will introduce our recent progress on graph-level neural operator development. In particular, we will examine three challenging tasks that are key to the success of graph search: (1) How can we conduct efficient graph similarity search by turning the NP-Complete problems, such as the Graph Edit Distance (GED) and Maximum Common Subgraph (MCS) computation, into a learning problem? We will present SimGNN [1] and GraphSim [3] that are able to provide more efficient and effective results compared to state-of-the-art approximate algorithms. (2) How can we provide a neural operator that can turn any graph into a low dimensional representation vector, which is learnable, inductive, and unsupervised? In this line, we propose UGraphEmd [2] that is able to leverage graph-graph interaction to produce manifold-preserving graph-level embedding. Moreover, GHashing [5] is designed to map each graph to a discrete hash code, which enables a much more efficient search (20 times speed up) to handle large graph database with millions of graphs. And (3) how can we design GNNs that can directly detect the best matched subgraphs of two graphs? A deep reinforcement learning framework RLMCS [4] is then proposed to address this issue, with the goal to learn the best strategy to pick the next matching pair for two graphs. In the end, we will provide some discussions to the open questions in the field.

Predicting missing facts in a knowledge graph (KG) is a crucial task in knowledge base construction and reasoning, and it has been the subject of much research in recent works using KG embeddings. While existing KG embedding approaches mainly learn and predict facts within a single KG, a more plausible solution would benefit from the knowledge in multiple language-specific KGs, considering that different KGs have their own strengths and limitations on data quality and coverage. This is quite challenging, since the transfer of knowledge among multiple independently maintained KGs is often hindered by the insufficiency of alignment information and the inconsistency of described facts. In this paper, we propose KEnS, a novel framework for embedding learning and ensemble knowledge transfer across a number of language-specific KGs. KEnS embeds all KGs in a shared embedding space, where the association of entities is captured based on self-learning. Then, KEnS performs ensemble inference to combine prediction results from embeddings of multiple language-specific KGs, for which multiple ensemble techniques are investigated. Experiments on five real-world language-specific KGs show that KEnS consistently improves state-of-the-art methods on KG completion, via effectively identifying and leveraging complementary knowledge., Comment: Findings of EMNLP 2020

Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data. However, most GNNs are designed for homogeneous graphs, in which all nodes and edges belong to the same types, making them infeasible to represent heterogeneous structures. In this paper, we present the Heterogeneous Graph Transformer (HGT) architecture for modeling Web-scale heterogeneous graphs. To model heterogeneity, we design node- and edge-type dependent parameters to characterize the heterogeneous attention over each edge, empowering HGT to maintain dedicated representations for different types of nodes and edges. To handle dynamic heterogeneous graphs, we introduce the relative temporal encoding technique into HGT, which is able to capture the dynamic structural dependency with arbitrary durations. To handle Web-scale graph data, we design the heterogeneous mini-batch graph sampling algorithm---HGSampling---for efficient and scalable training. Extensive experiments on the Open Academic Graph of 179 million nodes and 2 billion edges show that the proposed HGT model consistently outperforms all the state-of-the-art GNN baselines by 9%--21% on various downstream tasks., Comment: Published on WWW 2020

We aim at solving the problem of predicting people's ideology, or political tendency. We estimate it by using Twitter data, and formalize it as a classification problem. Ideology-detection has long been a challenging yet important problem. Certain groups, such as the policy makers, rely on it to make wise decisions. Back in the old days when labor-intensive survey-studies were needed to collect public opinions, analyzing ordinary citizens' political tendencies was uneasy. The rise of social medias, such as Twitter, has enabled us to gather ordinary citizen's data easily. However, the incompleteness of the labels and the features in social network datasets is tricky, not to mention the enormous data size and the heterogeneousity. The data differ dramatically from many commonly-used datasets, thus brings unique challenges. In our work, first we built our own datasets from Twitter. Next, we proposed TIMME, a multi-task multi-relational embedding model, that works efficiently on sparsely-labeled heterogeneous real-world dataset. It could also handle the incompleteness of the input features. Experimental results showed that TIMME is overall better than the state-of-the-art models for ideology detection on Twitter. Our findings include: links can lead to good classification outcomes without text; conservative voice is under-represented on Twitter; follow is the most important relation to predict ideology; retweet and mention enhance a higher chance of like, etc. Last but not least, TIMME could be extended to other datasets and tasks in theory., Comment: In proceedings of KDD'20, Applied Data Science Track; 9 pages, 2 supplementary pages

Betweenness centrality (BC) is one of the most used centrality measures for network analysis, which seeks to describe the importance of nodes in a network in terms of the fraction of shortest paths that pass through them. It is key to many valuable applications, including community detection and network dismantling. Computing BC scores on large networks is computationally challenging due to high time complexity. Many approximation algorithms have been proposed to speed up the estimation of BC, which are mainly sampling-based. However, these methods are still prone to considerable execution time on large-scale networks, and their results are often exacerbated when small changes happen to the network structures. In this paper, we focus on identifying nodes with high BC in a graph, since many application scenarios are built upon retrieving nodes with top-k BC. Different from previous heuristic methods, we turn this task into a learning problem and design an encoder-decoder based framework to resolve the problem. More specifcally, the encoder leverages the network structure to encode each node into an embedding vector, which captures the important structural information of the node. The decoder transforms the embedding vector for each node into a scalar, which captures the relative rank of this node in terms of BC. We use the pairwise ranking loss to train the model to identify the orders of nodes regarding their BC. By training on small-scale networks, the learned model is capable of assigning relative BC scores to nodes for any unseen networks, and thus identifying the highly-ranked nodes. Comprehensive experiments on both synthetic and real-world networks demonstrate that, compared to representative baselines, our model drastically speeds up the prediction without noticeable sacrifce in accuracy, and outperforms the state-of-the-art by accuracy on several large real-world networks., Comment: 10 pages, 4 figures, 8 tables

Microcredit, very small loans given out without any collaterals, is a new form of financial instrument that serves the segment of population that are typically underserved by traditional financial services. When microcredit takes the form of lending over the internet, it has the advantage of easy online application process and fast funding for borrowers, as well as attractive rate of return for individual lenders. For platforms that facilitate such activities, the key challenge lies in risk management, i.e. adequately pricing each loan's risk so as to balance borrowers' lending cost and lenders' risk-adjusted return. In fact, identifying default borrowers is of critical importance for the ecosystem. Traditionally, credit risk depends heavily on borrowers' historical loan records. However, most borrowers do not have any bureau history, and therefore cannot provide sufficient loan records. In this paper, we study default prediction in online lending by using social behavior. Specifically, we based our work on a dataset provided by PPDai, one of the leading platforms in China. Our dataset consists of over 11 million users and more than 1.5 billion call logs between them. We establish a mobile network and explore social factors that predict borrowers' default. Based on this, we focused on cheating agents, who recruit and teach borrowers to cheat by providing false information and faking application materials. Cheating agents represent a type of default, especially detrimental to the system. We propose a novel probabilistic framework to identify default borrowers and cheating agents simultaneously. Experimental results on production dataset demonstrate significant improvement over several baseline methods. Moreover, our model can effectively identify cheating agents without any labels.

Brand mentioning is a type of word-of-mouth advertising method where a brand name is disclosed by social media users in posts. Recently, brand mentioning by influencers has raised great attention because of the strong viral effects on the huge fan base of influencers. In this paper, we study the brand mentioning practice of influencers. More specifically, we analyze a brand mentioning social network built on 18,523 Instagram influencers and 804,397 brand mentioning posts. As a result, we found four inspiring findings: (i) most influencers mention only a few brands in their posts; (ii) popular influencers tend to mention only popular brands while micro-influencers do not have a preference on brand popularity; (iii) audience have highly similar reactions to sponsored and non-sponsored posts; and (iv) compared to non-sponsored posts, sponsored brand mentioning posts favor fewer usertags and more hashtags with longer captions to exclusively promote the specific products. Moreover, we propose a neural network-based model to classify the sponsorship of posts utilizing network embedding and social media features. The experimental results show that our model achieves 80% accuracy and significantly outperforms baseline methods.

We introduce a novel approach to graph-level representation learning, which is to embed an entire graph into a vector space where the embeddings of two graphs preserve their graph-graph proximity. Our approach, UGRAPHEMB, is a general framework that provides a novel means to performing graph-level embedding in a completely unsupervised and inductive manner. The learned neural network can be considered as a function that receives any graph as input, either seen or unseen in the training set, and transforms it into an embedding. A novel graph-level embedding generation mechanism called Multi-Scale Node Attention (MSNA), is proposed. Experiments on five real graph datasets show that UGRAPHEMB achieves competitive accuracy in the tasks of graph classification, similarity ranking, and graph visualization., IJCAI 2019 camera ready version with supplementary material

We consider data analytics workloads on distributed architectures, in particular clusters of commodity machines. To find a job partitioning that minimizes running time, a cost model, which we more accurately refer to as makespan model, is needed. In attempting to find the simplest possible, but sufficiently accurate, such model, we explore piecewise linear functions of input, output, and computational complexity. They are abstract in the sense that they capture fundamental algorithm properties, but do not require explicit modeling of system and implementation details such as the number of disk accesses. We show how the simplified functional structure can be exploited by directly integrating the model into the makespan optimization process, reducing complexity by orders of magnitude. Experimental results provide evidence of good prediction quality and successful makespan optimization across a variety of cluster architectures.

Embedding models for deterministic Knowledge Graphs (KG) have been extensively studied, with the purpose of capturing latent semantic relations between entities and incorporating the structured knowledge they contain into machine learning. However, there are many KGs that model uncertain knowledge, which typically model the inherent uncertainty of relations facts with a confidence score, and embedding such uncertain knowledge represents an unresolved challenge. The capturing of uncertain knowledge will benefit many knowledge-driven applications such as question answering and semantic search by providing more natural characterization of the knowledge. In this paper, we propose a novel uncertain KG embedding model UKGE, which aims to preserve both structural and uncertainty information of relation facts in the embedding space. Unlike previous models that characterize relation facts with binary classification techniques, UKGE learns embeddings according to the confidence scores of uncertain relation facts. To further enhance the precision of UKGE, we also introduce probabilistic soft logic to infer confidence scores for unseen relation facts during training. We propose and evaluate two variants of UKGE based on different confidence score modeling strategies. Experiments are conducted on three real-world uncertain KGs via three tasks, i.e. confidence prediction, relation fact ranking, and relation fact classification. UKGE shows effectiveness in capturing uncertain knowledge by achieving promising results, and it consistently outperforms baselines on these tasks.

We consider data analytics workloads on distributed architectures, in particular clusters of commodity machines. To find a job partitioning that minimizes running time, a cost model, which we more accurately refer to as makespan model, is needed. In attempting to find the simplest possible, but sufficiently accurate, such model, we explore piecewise linear functions of input, output, and computational complexity. They are abstract in the sense that they capture fundamental algorithm properties, but do not require explicit modeling of system and implementation details such as the number of disk accesses. We show how the simplified functional structure can be exploited to reduce optimization cost. In the general case, we identify a lower bound that can be used for search-space pruning. For applications with homogeneous tasks, we further demonstrate how to directly integrate the model into the makespan optimization process, reducing search-space dimensionality and thus complexity by orders of magnitude. Experimental results provide evidence of good prediction quality and successful makespan optimization across a variety of operators and cluster architectures.

Deck building is a crucial component in playing Collectible Card Games (CCGs). The goal of deck building is to choose a fixed-sized subset of cards from a large card pool, so that they work well together in-game against specific opponents. Existing methods either lack flexibility to adapt to different opponents or require large computational resources, still making them unsuitable for any real-time or large-scale application. We propose a new deck recommendation system, named Q-DeckRec, which learns a deck search policy during a training phase and uses it to solve deck building problem instances. Our experimental results demonstrate Q-DeckRec requires less computational resources to build winning-effective decks after a training phase compared to several baseline methods., CIG 2018

With the recent availability of Electronic Health Records (EHR) and great opportunities they offer for advancing medical informatics, there has been growing interest in mining EHR for improving quality of care. Disease diagnosis due to its sensitive nature, huge costs of error, and complexity has become an increasingly important focus of research in past years. Existing studies model EHR by capturing co-occurrence of clinical events to learn their latent embeddings. However, relations among clinical events carry various semantics and contribute differently to disease diagnosis which gives precedence to a more advanced modeling of heterogeneous data types and relations in EHR data than existing solutions. To address these issues, we represent how high-dimensional EHR data and its rich relationships can be suitably translated into HeteroMed, a heterogeneous information network for robust medical diagnosis. Our modeling approach allows for straightforward handling of missing values and heterogeneity of data. HeteroMed exploits metapaths to capture higher level and semantically important relations contributing to disease diagnosis. Furthermore, it employs a joint embedding framework to tailor clinical event representations to the disease diagnosis goal. To the best of our knowledge, this is the first study to use Heterogeneous Information Network for modeling clinical data and disease diagnosis. Experimental results of our study show superior performance of HeteroMed compared to prior methods in prediction of exact diagnosis codes and general disease cohorts. Moreover, HeteroMed outperforms baseline models in capturing similarities of clinical events which are examined qualitatively through case studies.

Network embedding algorithms that map nodes in a network into a low-dimensional vector space are prevalent in recent years, due to their superior performance in many network-based tasks, such as clustering, classification, and link prediction. The main assumption of existing algorithms is that the learned latent representation for nodes should preserve the structure of the network, in terms of first-order or higher-order connectivity. In other words, nodes that are more similar will have higher probability to connect to each other. This phenomena is typically explained as homophily in network science. However, there is another factor usually neglected by the existing embedding algorithms, which is the popularity of a node. For example, celebrities in a social network usually receive numerous followers, which cannot be fully explained by the similarity of the two users. We denote this factor with the terminology "social rank»». We then propose a network embedding model that considers both of the two factors in link generation, and learn proximity-based embedding and social rank-based embedding separately. Rather than simply treating these two factors independent with each other, a carefully designed link generation model is proposed, which explicitly models the interdependency between these two types of embeddings. Experiments on several real-world datasets across different domains demonstrate the superiority of our novel network embedding model over the state-of-the-art methods.

Measuring network similarity is a fundamental data mining problem. The mainstream similarity measures mainly leverage the structural information regarding to the entities in the network without considering the network semantics. In the real world, the heterogeneous information networks (HINs) with rich semantics are ubiquitous. However, the existing network similarity doesn't generalize well in HINs because they fail to capture the HIN semantics. The meta-path has been proposed and demonstrated as a right way to represent semantics in HINs. Therefore, original meta-path based similarities (e.g., PathSim and KnowSim) have been successful in computing the entity proximity in HINs. The intuition is that the more instances of meta-path(s) between entities, the more similar the entities are. Thus the original meta-path similarity only applies to computing the proximity of two neighborhood (connected) entities. In this paper, we propose the distant meta-path similarity that is able to capture HIN semantics between two distant (isolated) entities to provide more meaningful entity proximity. The main idea is that even there is no shared neighborhood entities of (i.e., no meta-path instances connecting) the two entities, but if the more similar neighborhood entities of the entities are, the more similar the two entities should be. We then find out the optimum distant meta-path similarity by exploring the similarity hypothesis space based on different theoretical foundations. We show the state-of-the-art similarity performance of distant meta-path similarity on two text-based HINs and make the datasets public available.

Social media websites have become a popular outlet for online users to express their opinions on controversial issues, such as gun control and abortion. Understanding users' stances and their arguments is a critical task for policy-making process and public deliberation. Existing methods rely on large amounts of human annotation for predicting stance on issues of interest, which is expensive and hard to scale to new problems. In this work, we present a weakly-guided user stance modeling framework which simultaneously considers two types of information: what do you say (via stance-based content generative model) and how do you behave (via social interaction-based graph regularization). We experiment with two types of social media data: news comments and discussion forum posts. Our model uniformly outperforms a logistic regression-based supervised method on stance-based link prediction for unseen users on news comments. Our method also achieves better or comparable stance prediction performance for discussion forum users, when compared with state-of-the-art supervised systems. Meanwhile, separate word distributions are learned for users of opposite stances. This potentially helps with better understanding and interpretation of conflicting arguments for controversial issues.

Almost all real-world social networks are dynamic and evolving with time, where new links may form and old links may drop, largely determined by the homophily of social actors (i.e., nodes in the network). Meanwhile, (latent) properties of social actors, such as their opinions, are changing along the time, partially due to social influence received from the network, which will in turn affect the network structure. Social network evolution and node property migration are usually treated as two orthogonal problems, and have been studied separately. In this paper, we propose a co-evolution model that closes the loop by modeling the two phenomena together, which contains two major components: (1) a network generative model when the node property is known; and (2) a property migration model when the social network structure is known. Simulation shows that our model has several nice properties: (1) it can model a broad range of phenomena such as opinion convergence (i.e., herding) and community-based opinion divergence; and (2) it allows to control the evolution via a set of factors such as social influence scope, opinion leader, and noise level. Finally, the usefulness of our model is demonstrated by an application of co-sponsorship prediction for legislative bills in Congress, which outperforms several state-of-the-art baselines.

Heterogeneous information networks (HINs) is a general representation of many real world applications. The difference between HIN and traditional homogeneous graphs is that the nodes and edges in HIN are with types. Then in the many applications, we need to consider the types to make the approach more semantically meaningful. For the applications that annotation is expensive, on natural way is to consider semi-supervised learning over HIN. In this paper, we present a semi-supervised learning algorithm constrained by the types of HINs. We first decompose the original HIN into several semantically meaningful sub-graphs based the meta-graphs composed of entity and relation types. Then we perform random walk over the sub-graphs to propagate the labels from labeled data to unlabeled data. After we obtain all the labels propagated by different trials of random walk guided by meta-graphs, we use an ensemble algorithm to vote for the final labeling results. We use two public available datasets, 20-newsgroups and RCV1 datasets to test our algorithm. Experimental results show that our algorithm is better than the traditional semi-supervised learning algorithms for HINs. One particular by-product of this work is that we show that previous random walk approach guided by meta-paths can be non-stationary, which is the major reason we propose a meta-graph guide random walk for semi-supervised learning over HINs.

Recent advances in neural networks have inspired people to design hybrid recommendation algorithms that can incorporate both (1) user-item interaction information and (2) content information including image, audio, and text. Despite their promising results, neural network-based recommendation algorithms pose extensive computational costs, making it challenging to scale and improve upon. In this paper, we propose a general neural network-based recommendation framework, which subsumes several existing state-of-the-art recommendation algorithms, and address the efficiency issue by investigating sampling strategies in the stochastic gradient descent training for the framework. We tackle this issue by first establishing a connection between the loss functions and the user-item interaction bipartite graph, where the loss function terms are defined on links while major computation burdens are located at nodes. We call this type of loss functions "graph-based" loss functions, for which varied mini-batch sampling strategies can have different computational costs. Based on the insight, three novel sampling strategies are proposed, which can significantly improve the training efficiency of the proposed framework (up to $\times 30$ times speedup in our experiments), as well as improving the recommendation performance. Theoretical analysis is also provided for both the computational cost and the convergence. We believe the study of sampling strategies have further implications on general graph-based loss functions, and would also enable more research under the neural network-based recommendation framework., This is a longer version (with supplementary attached) of the KDD'17 paper

With the rapid development of location-based social networks (LBSNs), spatial item recommendation has become an important mobile application, especially when users travel away from home. However, this type of recommendation is very challenging compared to traditional recommender systems. A user may visit only a limited number of spatial items, leading to a very sparse user-item matrix. This matrix becomes even sparser when the user travels to a distant place, as most of the items visited by a user are usually located within a short distance from the user’s home. Moreover, user interests and behavior patterns may vary dramatically across different time and geographical regions. In light of this, we propose ST-SAGE, a spatial-temporal sparse additive generative model for spatial item recommendation in this article. ST-SAGE considers both personal interests of the users and the preferences of the crowd in the target region at the given time by exploiting both the co-occurrence patterns and content of spatial items. To further alleviate the data-sparsity issue, ST-SAGE exploits the geographical correlation by smoothing the crowd’s preferences over a well-designed spatial index structure called the spatial pyramid . To speed up the training process of ST-SAGE, we implement a parallel version of the model inference algorithm on the GraphLab framework. We conduct extensive experiments; the experimental results clearly demonstrate that ST-SAGE outperforms the state-of-the-art recommender systems in terms of recommendation effectiveness, model training efficiency, and online recommendation efficiency.

Matchmaking connects multiple players to participate in online player-versus-player games. Current matchmaking systems depend on a single core strategy: create fair games at all times. These systems pair similarly skilled players on the assumption that a fair game is best player experience. We will demonstrate, however, that this intuitive assumption sometimes fails and that matchmaking based on fairness is not optimal for engagement. In this paper, we propose an Engagement Optimized Matchmaking (EOMM) framework that maximizes overall player engagement. We prove that equal-skill based matchmaking is a special case of EOMM on a highly simplified assumption that rarely holds in reality. Our simulation on real data from a popular game made by Electronic Arts, Inc. (EA) supports our theoretical results, showing significant improvement in enhancing player engagement compared to existing matchmaking methods., WWW2017

Nowadays social media, such as Twitter and all kinds of online forums, becomes a platform where people can express their opinions implicitly or explicitly. For example, in Twitter, people follow people they trust, and retweet the tweets they agree. In online forums, such as PoliticalForum.com, people explicitly express their opinions and interact with each other using text. Our goal is to understand people's stance on some (political) issue according to their online behaviors that can be captured in social media, including links they have issued and content they have generated, which is essential for national security and policy making. Existing attempts in this direction, however, oversimplified the problem in several aspects. First, they usually treat the user stance prediction problem as a binary classification problem, e.g., left or right, or positive or negative, while the extent of people's attitude is very critical. Second, most of the existing work depends heavily on labels, which is unacceptable for large-scale social media data and impossible to label when user stance is modeled as a numerical number. Third, most of the methods do not attempt to understand the rationality behind their online behaviors. In contrast, (1) our proposed methods can predict user stance in terms of numerical values; (2) our methods are unsupervised methods and no labels are required for the analysis; and (3) the models are carefully designed with the consideration of human rationality of their choices. In particular, two specific user stance prediction problems will be included in this keynote: (1) political ideology detection for ordinary twitter users via their heterogeneous types of links; and (2) user stance prediction in news commenting system. These methodologies may benefit more applications ranging across a wide spectrum of domains.

Recommendation has received tremendous attention recently due to its wide and successful applications across different domains. Different from traditional setting of recommendation tasks, modern recommendation tasks are usually exposed in a context-rich environment. For example, in addition to a user-item rating matrix, users and items are connected to other objects via different relationships and they are usually associated with rich attributes, such as text and spatio-temporal information. It turns out that heterogeneous information network serves a natural data model to capture the rich context of these recommendation tasks. In this tutorial, we will systematically introduce the methodologies of using heterogeneous information network mining approach to solve recommendation tasks, and demonstrate the effectiveness of such methods using different applications, ranging from collaboration recommendation in scientific research network to job recommendation in professional social network, and to drug discovery in biomedical networks. The topics to be covered in the tutorial include: (1) overall introduction; (2) recommendation in heterogeneous information networks, which introduces the general methodology of how to model the recommendation problem as a heterogeneous information network mining problem; (3) recommendation in a text-rich setting, where the information network is further enriched by refined analysis of text information; (4) recommendation with spatio-temporal information, where entities and relationships in the network are associated with spatio-temporal attributes; and (5) research frontiers for context-rich recommendation.

In this paper, we study the problem of author identification under double-blind review setting, which is to identify potential authors given information of an anonymized paper. Different from existing approaches that rely heavily on feature engineering, we propose to use network embedding approach to address the problem, which can automatically represent nodes into lower dimensional feature vectors. However, there are two major limitations in recent studies on network embedding: (1) they are usually general-purpose embedding methods, which are independent of the specific tasks; and (2) most of these approaches can only deal with homogeneous networks, where the heterogeneity of the network is ignored. Hence, challenges faced here are two folds: (1) how to embed the network under the guidance of the author identification task, and (2) how to select the best type of information due to the heterogeneity of the network. To address the challenges, we propose a task-guided and path-augmented heterogeneous network embedding model. In our model, nodes are first embedded as vectors in latent feature space. Embeddings are then shared and jointly trained according to task-specific and network-general objectives. We extend the existing unsupervised network embedding to incorporate meta paths in heterogeneous networks, and select paths according to the specific task. The guidance from author identification task for network embedding is provided both explicitly in joint training and implicitly during meta path selection. Our experiments demonstrate that by using path-augmented network embedding with task guidance, our model can obtain significantly better accuracy at identifying the true authors comparing to existing methods., Accepted by WSDM 2017. This is an extended version with appendix

Database analytics algorithms leverage quantifiable structural properties of the data to predict interesting concepts and relationships. The same information, however, can be represented using many different structures and the structural properties observed over particular representations do not necessarily hold for alternative structures. Because these algorithms tend to be highly effective over some choices of structure, such as that of the databases used to validate them, but not so effective with others, database analytics has largely remained the province of experts who can find the desired forms for these algorithms. We argue that in order to make database analytics usable, we should use or develop algorithms that are effective over a wide range of choices of structural organizations. We introduce the notion of representation independence and empirically analyze the amount of representation independence of some popular database analytics algorithms. Our results indicate that most algorithms are not generally representation independent and find some characteristics of more representation independent heuristics.

A heterogeneous information network (HIN) is a graph model in which objects and edges are annotated with types. Large and complex databases, such as YAGO and DBLP, can be modeled as HINs. A fundamental problem in HINs is the computation of closeness, or relevance, between two HIN objects. Relevance measures can be used in various applications, including entity resolution, recommendation, and information retrieval. Several studies have investigated the use of HIN information for relevance computation, however, most of them only utilize simple structure, such as path, to measure the similarity between objects. In this paper, we propose to use meta structure, which is a directed acyclic graph of object types with edge types connecting in between, to measure the proximity between objects. The strength of meta structure is that it can describe complex relationship between two HIN objects (e.g., two papers in DBLP share the same authors and topics). We develop three relevance measures based on meta structure. Due to the computational complexity of these measures, we further design an algorithm with data structures proposed to support their evaluation. Our extensive experiments on YAGO and DBLP show that meta structure-based relevance is more effective than state-of-the-art approaches, and can be efficiently computed.

Online dating sites have become popular platforms for people to look for potential romantic partners. Different from traditional user-item recommendations where the goal is to match items (e.g., books, videos) with a user’s interests, a recommendation system for online dating aims to match people who are mutually interested in and likely to communicate with each other. We introduce similarity measures that capture the unique features and characteristics of the online dating network, for example, the interest similarity between two users if they send messages to same users, and attractiveness similarity if they receive messages from same users. A reciprocal score that measures the compatibility between a user and each potential dating candidate is computed, and the recommendation list is generated to include users with top scores. The performance of our proposed recommendation system is evaluated on a real-world dataset from a major online dating site in China. The results show that our recommendation algorithms significantly outperform previously proposed approaches, and the collaborative filtering-based algorithms achieve much better performance than content-based algorithms in both precision and recall. Our results also reveal interesting behavioral difference between male and female users when it comes to looking for potential dates. In particular, males tend to be focused on their own interest and oblivious toward their attractiveness to potential dates, while females are more conscientious to their own attractiveness to the other side of the line.

Background In the context of drug discovery, drug target interactions (DTIs) can be predicted based on observed topological features of a semantic network across the chemical and biological space. In a semantic network, the types of the nodes and links are different. In order to take into account the heterogeneity of the semantic network, meta-path-based topological patterns were investigated for link prediction. Results Supervised machine learning models were constructed based on meta-path topological features of an enriched semantic network, which was derived from Chem2Bio2RDF, and was expanded by adding compound and protein similarity neighboring links obtained from the PubChem databases. The additional semantic links significantly improved the predictive performance of the supervised learning models. The binary classification model built upon the enriched feature space using the Random Forest algorithm significantly outperformed an existing semantic link prediction algorithm, Semantic Link Association Prediction (SLAP), to predict unknown links between compounds and protein targets in an evolving network. In addition to link prediction, Random Forest also has an intrinsic feature ranking algorithm, which can be used to select the important topological features that contribute to link prediction. Conclusions The proposed framework has been demonstrated as a powerful alternative to SLAP in order to predict DTIs using the semantic network that integrates chemical, pharmacological, genomic, biological, functional, and biomedical information into a unified framework. It offers the flexibility to enrich the feature space by using different normalization processes on the topological features, and it can perform model construction and feature selection at the same time. Electronic supplementary material The online version of this article (doi:10.1186/s12859-016-1005-x) contains supplementary material, which is available to authorized users.

Recommender systems typically leverage two types of signals to effectively recommend items to users: user activities and content matching between user and item profiles, and recommendation models in literature are usually categorized into collaborative filtering models, content-based models and hybrid models. In practice, when rich profiles about users and items are available, and user activities are sparse (cold-start), effective content matching signals become much more important in the relevance of the recommendation. The de-facto method to measure similarity between two pieces of text is computing the cosine similarity of the two bags of words, and each word is weighted by TF (term frequency within the document) x IDF (inverted document frequency of the word within the corpus). In general sense, TF can represent any local weighting scheme of the word within each document, and IDF can represent any global weighting scheme of the word across the corpus. In this paper, we focus on the latter, i.e., optimizing the global term weights, for a particular recommendation domain by leveraging supervised approaches. The intuition is that some frequent words (lower IDF, e.g. ``database'') can be essential and predictive for relevant recommendation, while some rare words (higher IDF, e.g. the name of a small company) could have less predictive power. Given plenty of observed activities between users and items as training data, we should be able to learn better domain-specific global term weights, which can further improve the relevance of recommendation. We propose a unified method that can simultaneously learn the weights of multiple content matching signals, as well as global term weights for specific recommendation tasks. Our method is efficient to handle large-scale training data generated by production recommender systems. And experiments on LinkedIn job recommendation data justify the effectiveness of our approach.

In this paper, we describe the WSDM Cup entity ranking challenge held in conjunction with the 2016 Web Search and Data Mining conference (WSDM 2016). Participants in the challenge were provided access to the Microsoft Academic Graph (MAG), a large heterogeneous graph of academic entities, and were invited to calculate the query-independent importance of each publication in the graph. Submissions for the challenge were open from August through November 2015, and a public leaderboard displayed teams? progress against a set of training judgements. Final evaluations were performed against a separate, withheld portion of the evaluation judgements. The top eight performing teams were then invited to submit papers to the WSDM Cup workshop, held at the WSDM 2016 conference.

With the rapid development of location-based social networks (LBSNs), spatial item recommendation has become an important means to help people discover attractive and interesting venues and events, especially when users travel out of town. However, this recommendation is very challenging compared to the traditional recommender systems. A user can visit only a limited number of spatial items, leading to a very sparse user-item matrix. Most of the items visited by a user are located within a short distance from where he/she lives, which makes it hard to recommend items when the user travels to a far away place. Moreover, user interests and behavior patterns may vary dramatically across different geographical regions. In light of this, we propose Geo-SAGE, a geographical sparse additive generative model for spatial item recommendation in this paper. Geo-SAGE considers both user personal interests and the preference of the crowd in the target region, by exploiting both the co-occurrence pattern of spatial items and the content of spatial items. To further alleviate the data sparsity issue, Geo-SAGE exploits the geographical correlation by smoothing the crowd's preferences over a well-designed spatial index structure called spatial pyramid. We conduct extensive experiments to evaluate the performance of our Geo-SAGE model on two real large-scale datasets. The experimental results clearly demonstrate our Geo-SAGE model outperforms the state-of-the-art in the two tasks of both out-of-town and home-town recommendations., 10 pages, 15 figures

Most real systems consist of a large number of interacting, multi-typed components, while most contemporary researches model them as homogeneous networks, without distinguishing different types of objects and links in the networks. Recently, more and more researchers begin to consider these interconnected, multi-typed data as heterogeneous information networks, and develop structural analysis approaches by leveraging the rich semantic meaning of structural types of objects and links in the networks. Compared to widely studied homogeneous network, the heterogeneous information network contains richer structure and semantic information, which provides plenty of opportunities as well as a lot of challenges for data mining. In this paper, we provide a survey of heterogeneous information network analysis. We will introduce basic concepts of heterogeneous information network analysis, examine its developments on different data mining tasks, discuss some advanced topics, and point out some future research directions., Comment: 45 pages, 12 figures

Cyber-Physical System (CPS) is an integration of distributed sensor networks with computational devices. CPS claims many promising applications, such as traffic observation, battlefield surveillance, and sensor-network-based monitoring. One important topic in CPS research is about the atypical event analysis, that is, retrieving the events from massive sensor data and analyzing them with spatial, temporal, and other multidimensional information. Many traditional methods are not feasible for such analysis since they cannot describe the complex atypical events. In this paper, we propose a novel model of atypical cluster to effectively represent such events and efficiently retrieve them from massive data. The basic cluster is designed to summarize an individual event, and the macrocluster is used to integrate the information from multiple events. To facilitate scalable, flexible, and online analysis, the atypical cube is constructed, and a guided clustering algorithm is proposed to retrieve significant clusters in an efficient manner. We conduct experiments on real sensor datasets with the size of more than 50 GB; the results show that the proposed method can provide more accurate information with only 15% to 20% time cost of the baselines.

With the rapid development of online social media, online shopping sites and cyber-physical systems, heterogeneous information networks have become increasingly popular and content-rich over time. In many cases, such networks contain multiple types of objects and links, as well as different kinds of attributes. The clustering of these objects can provide useful insights in many applications. However, the clustering of such networks can be challenging since (a) the attribute values of objects are often incomplete, which implies that an object may carry only partial attributes or even no attributes to correctly label itself; and (b) the links of different types may carry different kinds of semantic meanings, and it is a difficult task to determine the nature of their relative importance in helping the clustering for a given purpose. In this paper, we address these challenges by proposing a model-based clustering algorithm. We design a probabilistic model which clusters the objects of different types into a common hidden space, by using a user-specified set of attributes, as well as the links from different relations. The strengths of different types of links are automatically learned, and are determined by the given purpose of clustering. An iterative algorithm is designed for solving the clustering problem, in which the strengths of different types of links and the quality of clustering results mutually enhance each other. Our experimental results on real and synthetic data sets demonstrate the effectiveness and efficiency of the algorithm., Comment: VLDB2012

Question Routing (QR) on Community-based Question Answering (CQA) websites aims at recommending answerers that have high probabilities of providing the “accepted answers” to new questions. The existing question routing algorithms simply predict the ranking of users based on query content. As a consequence, the question raiser information is ignored. On the other hand, they lack learnable scoring functions to explicitly compute ranking scores.To tackle these challenges, we propose NeRank that (1) jointly learns representations of question content, question raiser, and question answerers by a heterogeneous information network embedding algorithm and a long short-term memory (LSTM) model. The embeddings of the three types of entities are unified in the same latent space, and (2) conducts question routing for personalized queries, i.e., queries with two entities (question content, question raiser), by a convolutional scoring function taking the learned embeddings of all three types of entities as input. Using the scores, NeRank routes new questions to high-ranking answerers that are skillfulness in the question domain and have similar backgrounds to the question raiser.Experimental results show that NeRank significantly outperforms competitive baseline question routing models that ignore the raiser information in three ranking metrics. In addition, NeRank is convergeable in several thousand iterations and insensitive to parameter changes, which prove its effectiveness, scalability, and robustness.

Graph similarity computation is one of the core operations in many graph-based applications, such as graph similarity search, graph database analysis, graph clustering, etc. Since computing the exact distance/similarity between two graphs is typically NP-hard, a series of approximate methods have been proposed with a trade-off between accuracy and speed. Recently, several data-driven approaches based on neural networks have been proposed, most of which model the graph-graph similarity as the inner product of their graph-level representations, with different techniques proposed for generating one embedding per graph. However, using one fixed-dimensional embedding per graph may fail to fully capture graphs in varying sizes and link structures—a limitation that is especially problematic for the task of graph similarity computation, where the goal is to find the fine-grained difference between two graphs. In this paper, we address the problem of graph similarity computation from another perspective, by directly matching two sets of node embeddings without the need to use fixed-dimensional vectors to represent whole graphs for their similarity computation. The model, Graph-Sim, achieves the state-of-the-art performance on four real-world graph datasets under six out of eight settings (here we count a specific dataset and metric combination as one setting), compared to existing popular methods for approximate Graph Edit Distance (GED) and Maximum Common Subgraph (MCS) computation.