通过图划分实现节点可解释性并行计算，大幅提速且不损失准确性。
Parallelizing Node-Level Explainability in Graph Neural Networks
- 将图划分为不相交子图，实现邻居节点解释并行计算。
- 在真实数据集上实现显著加速，支持大规模GNN模型可解释性。
- 适合需要高效透明解释的大规模图神经网络应用场景。
图神经网络（GNN）在节点分类、链接预测和图分类等任务中表现优异，充分利用了图结构数据的拓扑信息。然而，在节点分类任务中，随着图规模增大，计算节点级可解释性变得极其耗时，而常见的批处理策略往往损害解释质量。本文提出一种通过图划分实现GNN节点级可解释性并行的新方法。通过将图分解为互不重叠的子图，可并行计算节点邻居的解释，显著提升可扩展性和效率，且在内存充足时保证结果正确性。针对内存受限场景，进一步设计基于丢弃（dropout）的重构机制，可在内存占用与解释保真度间实现可控权衡。在真实数据集上的实验表明，该方法带来显著加速，实现了大规模GNN模型的可扩展且透明的可解释性。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have demonstrated remarkable performance in a wide range of tasks, such as node classification, link prediction, and graph classification, by exploiting the structural information in graph-structured data. However, in node classification, computing node-level explainability becomes extremely time-consuming as the size of the graph increases, while batching strategies often degrade explanation quality. This paper introduces a novel approach to parallelizing node-level explainability in GNNs through graph partitioning. By decomposing the graph into disjoint subgraphs, we enable parallel computation of explainability for node neighbors, significantly improving the scalability and efficiency without affecting the correctness of the results, provided sufficient memory is available. For scenarios where memory is limited, we further propose a dropout-based reconstruction mechanism that offers a controllable trade-off between memory usage and explanation fidelity. Experimental results on real-world datasets demonstrate substantial speedups, enabling scalable and transparent explainability for large-scale GNN models.
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。