Showing 2024Show all
3 papers · 1 filter
cs.LG2024
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.DC2024
A Unified CPU-GPU Protocol for GNN Training
Yi-Chien Lin, Gangda Deng, Viktor Prasanna
Training a Graph Neural Network (GNN) model on large-scale graphs involves a high volume of data communication and computations. While state-of-the-art CPUs and GPUs feature high c…
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…