49 citations · 134 across the 11 of their papers we have counts for
7 papers · 1 filter
SPEED: Streaming Partition and Parallel Acceleration for Temporal Interaction Graph Embedding
Xi Chen, Yongxiang Liao, Yun Xiong +4
Temporal Interaction Graphs (TIGs) are widely employed to model intricate real-world systems such as financial systems and social networks. To capture the dynamism and interdepende…
RDGSL: Dynamic Graph Representation Learning with Structure Learning
Siwei Zhang, Yun Xiong, Yao Zhang +4
Temporal Graph Networks (TGNs) have shown remarkable performance in learning representation for continuous-time dynamic graphs. However, real-world dynamic graphs typically contain…
iLoRE: Dynamic Graph Representation with Instant Long-term Modeling and Re-occurrence Preservation
Siwei Zhang, Yun Xiong, Yao Zhang +3
Continuous-time dynamic graph modeling is a crucial task for many real-world applications, such as financial risk management and fraud detection. Though existing dynamic graph mode…
TIGER: Temporal Interaction Graph Embedding with Restarts
Yao Zhang, Yun Xiong, Yongxiang Liao +4
Temporal interaction graphs (TIGs), consisting of sequences of timestamped interaction events, are prevalent in fields like e-commerce and social networks. To better learn dynamic…
RuDi: Explaining Behavior Sequence Models by Automatic Statistics Generation and Rule Distillation
Yao Zhang, Yun Xiong, Yiheng Sun +4
Risk scoring systems have been widely deployed in many applications, which assign risk scores to users according to their behavior sequences. Though many deep learning methods with…
ReCo: A Dataset for Residential Community Layout Planning
Xi Chen, Yun Xiong, Siqi Wang +4
Layout planning is centrally important in the field of architecture and urban design. Among the various basic units carrying urban functions, residential community plays a vital pa…
Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning
Yizhu Jiao, Yun Xiong, Jiawei Zhang +3
Graph representation learning has attracted lots of attention recently. Existing graph neural networks fed with the complete graph data are not scalable due to limited computation…