Abstract:Explaining graph neural networks (GNNs) has become more and more important recently. Higher-order interpretation schemes, such as GNN-LRP (layer-wise relevance propagation for GNN), emerged as powerful tools for unraveling how different features interact thereby contributing to explaining GNNs. GNN-LRP gives a relevance attribution of walks between nodes at each layer, and the subgraph attribution is expressed as a sum over exponentially many such walks. In this work, we demonstrate that such exponential complexity can be avoided. In particular, we propose novel algorithms that enable to attribute subgraphs with GNN-LRP in linear-time (w.r.t. the network depth). Our algorithms are derived via message passing techniques that make use of the distributive property, thereby directly computing quantities for higher-order explanations. We further adapt our efficient algorithms to compute a generalization of subgraph attributions that also takes into account the neighboring graph features. Experimental results show the significant acceleration of the proposed algorithms and demonstrate the high usefulness and scalability of our novel generalized subgraph attribution method.
| Comments: | Published in ICML 2022 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.22385 [cs.LG] |
| (or arXiv:2605.22385v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22385 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Proceedings of the 39th International Conference on Machine Learning, PMLR 162:24478-24495, 2022 |
From: Ping Xiong [view email]
[v1]
Thu, 21 May 2026 12:16:19 UTC (1,780 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。