57 citations · 208 across the 13 of their papers we have counts for
4 papers · 1 filter
Learning Hierarchical Protein Representations via Complete 3D Graph Networks
Limei Wang, Haoran Liu, Yi Liu +2
We consider representation learning for proteins with 3D structures. We build 3D graphs based on protein structures and develop graph networks to learn their representations. Depen…
GraphFM: Improving Large-Scale GNN Training via Feature Momentum
Haiyang Yu, Limei Wang, Bokun Wang +3
Training of graph neural networks (GNNs) for large-scale node classification is challenging. A key difficulty lies in obtaining accurate hidden node representations while avoiding…
ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs
Limei Wang, Yi Liu, Yuchao Lin +2
Many real-world data can be modeled as 3D graphs, but learning representations that incorporates 3D information completely and efficiently is challenging. Existing methods either u…
GOOD: A Graph Out-of-Distribution Benchmark
Shurui Gui, Xiner Li, Limei Wang +1
Out-of-distribution (OOD) learning deals with scenarios in which training and test data follow different distributions. Although general OOD problems have been intensively studied…