June 10, 2024, 4:45 a.m. | Xizhi Gu, Hongzheng Li, Shihong Gao, Xinyan Zhang, Lei Chen, Yingxia Shao

cs.LG updates on arXiv.org arxiv.org

arXiv:2406.04938v1 Announce Type: new
Abstract: 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 and encounters the Out-of-Memory problem when handling large graphs. To address this memory problem, a popular solution is mini-batch GNN training. However, mini-batch GNN training increases the training variance and sacrifices the model accuracy. In this paper, we propose a new memory-efficient GNN training method using spanning subgraph, called …

abstract accuracy arxiv capability cs.ai cs.lg data gnn gnns graph graph data graph neural networks graphs however memory networks neural networks peak popular problem solution training type usage via

Senior Data Engineer

@ Displate | Warsaw

Solution Architect

@ Philips | Bothell - B2 - Bothell 22050

Senior Product Development Engineer - Datacenter Products

@ NVIDIA | US, CA, Santa Clara

Systems Engineer - 2nd Shift (Onsite)

@ RTX | PW715: Asheville Site W Asheville Greenfield Site TBD , Asheville, NC, 28803 USA

System Test Engineers (HW & SW)

@ Novanta | Barcelona, Spain

Senior Solutions Architect, Energy

@ NVIDIA | US, TX, Remote