3 papers
cs.LG2025
Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants
Gangda Deng, Hongkuan Zhou, Rajgopal Kannan +1
Heterophilous graphs, where dissimilar nodes tend to connect, pose a challenge for graph neural networks (GNNs). Increasing the GNN depth can expand the scope (i.e., receptive fiel…
cs.LG2024
Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours
Yuxin Yang, Hongkuan Zhou, Rajgopal Kannan +1
Temporal Graph Neural Networks (TGNNs) have emerged as powerful tools for modeling dynamic interactions across various domains. The design space of TGNNs is notably complex, given…
cs.LG2024
TASER: Temporal Adaptive Sampling for Fast and Accurate Dynamic Graph Representation Learning
Gangda Deng, Hongkuan Zhou, Hanqing Zeng +5
Recently, Temporal Graph Neural Networks (TGNNs) have demonstrated state-of-the-art performance in various high-impact applications, including fraud detection and content recommend…