• Publications
  • Influence
The Semantic Web
TLDR
Contrastive reasoning is the reasoning with contrasts which are expressed as contrary conjunctions like the word ”but” in natural language. Expand
  • 3,972
  • 368
ArnetMiner: extraction and mining of academic social networks
TLDR
This paper addresses several key issues in the ArnetMiner system, which aims at extracting and mining academic social networks. Expand
  • 1,410
  • 161
  • PDF
RiMOM: A Dynamic Multistrategy Ontology Alignment Framework
TLDR
We propose a systematic approach to quantitatively estimate the similarity characteristics for each alignment task and propose a strategy selection method to automatically combine the matching strategies based on estimated factors. Expand
  • 429
  • 39
  • PDF
Social Influence Locality for Modeling Retweeting Behaviors
TLDR
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. Expand
  • 183
  • 24
  • PDF
Multi-Channel Graph Neural Network for Entity Alignment
TLDR
We propose a novel Multi-channel Graph Neural Network model (MuGNN) to learn alignment-oriented knowledge graph (KG) embeddings by robustly encoding two KGs via multiple channels. Expand
  • 48
  • 17
  • PDF
Who Influenced You? Predicting Retweet via Social Influence Locality
TLDR
Social influence occurs when one’s opinions, emotions, or behaviors are affected by others in a social network. Expand
  • 88
  • 14
  • PDF
Social context summarization
TLDR
We study a novel problem of social context summarization for Web documents by considering both the informativeness of sentences and interests of social users. Expand
  • 99
  • 13
  • PDF
Using Bayesian decision for ontology mapping
TLDR
An approach called Risk Minimization based Ontology Mapping (RiMOM) is proposed, which automates the discovery of ontology mapping. Expand
  • 198
  • 12
  • PDF
Text-Enhanced Representation Learning for Knowledge Graph
TLDR
We propose a novel knowledge graph representation learning method by taking advantage of the rich context information in a text corpus to expand the semantic structure of the knowledge graph. Expand
  • 109
  • 12
  • PDF
OpenKE: An Open Toolkit for Knowledge Embedding
TLDR
We release an open toolkit for knowledge embedding (OpenKE), which provides a unified framework and various fundamental models to embed knowledge graphs into a continuous low-dimensional space. Expand
  • 111
  • 12
  • PDF