4 papers
ParamSpMM: Adaptive and Efficient Sparse Matrix-Matrix Multiplication on GPUs for GNNs
Lixing Zhang, Guanhua Ye, Hongzheng Li +2
Fueled by the ability to mine real-world graph data, GNN applications have experienced phenomenal growth. Sparse Matrix-Matrix Multiplication (SpMM) is a critical operator in GNNs.…
Efficient Cross-Architecture Knowledge Transfer for Large-Scale Online User Response Prediction
Yucheng Wu, Yuekui Yang, Hongzheng Li +6
Deploying new architectures in large-scale user response prediction systems incurs high model switching costs due to expensive retraining on massive historical data and performance…
LAC: Graph Contrastive Learning with Learnable Augmentation in Continuous Space
Zhenyu Lin, Hongzheng Li, Yingxia Shao +3
Graph Contrastive Learning frameworks have demonstrated success in generating high-quality node representations. The existing research on efficient data augmentation methods and id…
SpanGNN: Towards Memory-Efficient Graph Neural Networks via Spanning Subgraph Training
Xizhi Gu, Hongzheng Li, Shihong Gao +3
Graph Neural Networks (GNNs) have superior capability in learning graph data. Full-graph GNN training generally has high accuracy, however, it suffers from large peak memory usage…