• Publications
  • Influence
ArnetMiner: extraction and mining of academic social networks
The architecture and main features of the ArnetMiner system, which aims at extracting and mining academic social networks, are described and a unified modeling approach to simultaneously model topical aspects of papers, authors, and publication venues is proposed. Expand
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
The NetMF method offers significant improvements over DeepWalk and LINE for conventional network mining tasks and provides the theoretical connections between skip-gram based network embedding algorithms and the theory of graph Laplacian. Expand
Social influence analysis in large-scale networks
Topical Affinity Propagation (TAP) is designed with efficient distributed learning algorithms that is implemented and tested under the Map-Reduce framework and can take results of any topic modeling and the existing network structure to perform topic-level influence propagation. Expand
RiMOM: A Dynamic Multistrategy Ontology Alignment Framework
This paper presents a dynamic multistrategy ontology alignment framework, named RiMOM, and proposes a systematic approach to quantitatively estimate the similarity characteristics for each alignment task and a strategy selection method to automatically combine the matching strategies based on two estimated factors. Expand
COSNET: Connecting Heterogeneous Social Networks with Local and Global Consistency
An efficient subgradient algorithm is developed to train the model by converting the original energy-based objective function into its dual form, and it is demonstrated that applying the integration results produced by the method can improve the accuracy of expert finding, an important task in social networks. Expand
User-level sentiment analysis incorporating social networks
It is shown that information about social relationships can be used to improve user-level sentiment analysis and incorporating social-network information can indeed lead to statistically significant sentiment classification improvements over the performance of an approach based on Support Vector Machines having access only to textual features. Expand
GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
Graph Contrastive Coding (GCC) is designed --- a self-supervised graph neural network pre-training framework --- to capture the universal network topological properties across multiple networks and leverage contrastive learning to empower graph neural networks to learn the intrinsic and transferable structural representations. Expand
Social Influence Locality for Modeling Retweeting Behaviors
We study an interesting phenomenon of social influence locality in a large microblogging network, which suggests that users' behaviors are mainly influenced by close friends in their ego networks. WeExpand
Cognitive Graph for Multi-Hop Reading Comprehension at Scale
The implementation based on BERT and graph neural network efficiently handles millions of documents for multi-hop reasoning questions in the HotpotQA fullwiki dataset, achieving a winning joint F_1 score of 34.9 on the leaderboard. Expand
A Unified Probabilistic Framework for Name Disambiguation in Digital Library
A disambiguation objective function for the name ambiguity problem is defined and a two-step parameter estimation algorithm is proposed, which significantly outperforms four baseline methods of using clustering algorithms and two other previous methods. Expand