3 papers
cs.DB2026
Dual-Metric Partitioning with Adaptive Kernel Execution for Efficient GCN Acceleration
Lingling Zhang, Hang Zeng, Pengpeng Qiao +3
Graph Convolutional Networks (GCNs) are widely used for large graph-structured data, including social, citation, and e-commerce networks, but their deployment is constrained by irr…
cs.DB2026
StreamTGN: A GPU-Efficient Serving System for Streaming Temporal Graph Neural Networks
Lingling Zhang, Pengpeng Qiao, Zhiwei Zhang +2
Temporal Graph Neural Networks (TGNs) achieve state-of-the-art performance on dynamic graph tasks, yet existing systems focus exclusively on accelerating training -- at inference t…
cs.SI2024
Influence Maximization in Hypergraphs by Stratified Sampling for Efficient Generation of Reverse Reachable Sets
Lingling Zhang, Hong Jiang, Ye Yuan +1
Given a hypergraph, influence maximization (IM) is to discover a seed set containing vertices that have the maximal influence. Although the existing vertex-based IM algorithms…