用分布式方法加速图神经网络解释，支持百万级特征
DistShap: Scalable GNN Explanations with Distributed Shapley Values
- 通过分布式采样子图并行计算边重要性
- 在128张GPU上实现百万特征模型的解释
- 首个可扩展至超大规模图神经网络的解释方法
随着图神经网络（GNN）应用日益广泛，解释其预测结果变得愈发重要。然而，将预测归因于特定边或特征仍面临巨大计算开销。例如，一个拥有100个邻居的节点使用3层GNN进行分类时，需从数百万候选边中识别关键贡献。为此，我们提出DistShap，一种基于分布式谢林值的并行解释算法。该方法在分布式环境下采样子图，跨多张GPU并行执行GNN推理，并求解分布式最小二乘问题以计算边重要性得分。DistShap在准确率上优于多数现有GNN解释方法，并首次实现对含百万级特征的GNN模型的可扩展解释，借助美国国家能源研究科学计算中心Perlmutter超级计算机上的128张GPU完成。
原文摘要 · Abstract (English)
With the growing adoption of graph neural networks (GNNs), explaining their predictions has become increasingly important. However, attributing predictions to specific edges or features remains computationally expensive. For example, classifying a node with 100 neighbors using a 3-layer GNN may involve identifying important edges from millions of candidates contributing to the prediction. To address this challenge, we propose DistShap, a parallel algorithm that distributes Shapley value-based explanations across multiple GPUs. DistShap operates by sampling subgraphs in a distributed setting, executing GNN inference in parallel across GPUs, and solving a distributed least squares problem to compute edge importance scores. DistShap outperforms most existing GNN explanation methods in accuracy and is the first to scale to GNN models with millions of features by using up to 128 GPUs on the NERSC Perlmutter supercomputer.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。