标题： DistShap：具有分布式Shapley值的可扩展GNN解释 显示英文标题

标题： DistShap: Scalable GNN Explanations with Distributed Shapley Values

摘要： 随着图神经网络（GNNs）的广泛采用，解释其预测结果变得越来越重要。 然而，将预测归因于特定的边或特征仍然计算成本高昂。 例如，使用三层GNN对具有100个邻居的节点进行分类可能需要从数百万个候选边中识别出对预测有贡献的重要边。 为了解决这一挑战，我们提出了DistShap，这是一种在多个GPU上分布Shapley值基础解释的并行算法。 DistShap通过在分布式环境中采样子图，在多个GPU上并行执行GNN推理，并求解分布式最小二乘问题来计算边的重要性得分。 DistShap在准确性方面优于大多数现有的GNN解释方法，并且是首个通过在NERSC Perlmutter超级计算机上使用多达128个GPU来扩展到具有数百万特征的GNN模型的方法。 显示英文摘要

摘要： 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.