Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2406.04938 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916279600807936 |
|---|---|
| author | Gu, Xizhi Li, Hongzheng Gao, Shihong Zhang, Xinyan Chen, Lei Shao, Yingxia |
| author_facet | Gu, Xizhi Li, Hongzheng Gao, Shihong Zhang, Xinyan Chen, Lei Shao, Yingxia |
| contents | 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 SpanGNN. SpanGNN trains GNN models over a sequence of spanning subgraphs, which are constructed from empty structure. To overcome the excessive peak memory consumption problem, SpanGNN selects a set of edges from the original graph to incrementally update the spanning subgraph between every epoch. To ensure the model accuracy, we introduce two types of edge sampling strategies (i.e., variance-reduced and noise-reduced), and help SpanGNN select high-quality edges for the GNN learning. We conduct experiments with SpanGNN on widely used datasets, demonstrating SpanGNN's advantages in the model performance and low peak memory usage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_04938 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SpanGNN: Towards Memory-Efficient Graph Neural Networks via Spanning Subgraph Training Gu, Xizhi Li, Hongzheng Gao, Shihong Zhang, Xinyan Chen, Lei Shao, Yingxia Machine Learning Artificial Intelligence 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 SpanGNN. SpanGNN trains GNN models over a sequence of spanning subgraphs, which are constructed from empty structure. To overcome the excessive peak memory consumption problem, SpanGNN selects a set of edges from the original graph to incrementally update the spanning subgraph between every epoch. To ensure the model accuracy, we introduce two types of edge sampling strategies (i.e., variance-reduced and noise-reduced), and help SpanGNN select high-quality edges for the GNN learning. We conduct experiments with SpanGNN on widely used datasets, demonstrating SpanGNN's advantages in the model performance and low peak memory usage. |
| title | SpanGNN: Towards Memory-Efficient Graph Neural Networks via Spanning Subgraph Training |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2406.04938 |