• Publications
  • Influence
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
  • 1,405
  • 159
  • PDF
Dota 2 with Large Scale Deep Reinforcement Learning
TLDR
We developed a distributed training system and tools for continual training which allowed us to train a Dota 2-playing agent called OpenAI Five for 10 months. Expand
  • 229
  • 21
  • PDF
Name Disambiguation in AMiner: Clustering, Maintenance, and Human in the Loop.
TLDR
We propose a novel representation learning method by incorporating both global and local information and present an end-to-end cluster size estimation method that is significantly better than traditional BIC-based method. Expand
  • 48
  • 11
  • PDF
Citation count prediction: learning to estimate future citations for literature
TLDR
We use the citations as a measurement for the popularity among researchers and study the interesting problem of Citation Count Prediction (CCP) to examine the characteristics for popularity. Expand
  • 118
  • 10
  • PDF
Result of Ontology Alignment with RiMOM at OAEI'06
TLDR
In this report, we briefly describe our system RiMOM and its underlying techniques. Expand
  • 56
  • 6
  • PDF
GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
TLDR
We design GCC's pre-training task as subgraph instance discrimination in and across networks and leverage contrastive learning to empower graph neural networks to learn the intrinsic and transferable structural representations. Expand
  • 30
  • 6
  • PDF
Expertise Matching via Constraint-Based Optimization
TLDR
This paper explores such an approach by formulating the expertise matching problem in a constraint based optimization framework, which guarantees an optimal solution under given constraints. Expand
  • 37
  • 3
Course Concept Expansion in MOOCs with External Knowledge and Interactive Game
TLDR
We propose a three-stage course concept expansion model that achieves an O(log logn) competitive ratio over existing methods. Expand
  • 5
  • 3
  • PDF
Enabling Deep Learning on IoT Devices
TLDR
Deep learning can enable Internet of Things (IoT) devices to interpret unstructured multimedia data and intelligently react to environmental events but has demanding performance and power requirements. Expand
  • 68
  • 2
Residual Feature Aggregation Network for Image Super-Resolution
TLDR
We propose a novel residual feature aggregation (RFA) framework, which aggregates the local residual features for more powerful feature representation. Expand
  • 18
  • 2
  • PDF