BriefGPT.xyz
Jun, 2023
消息传递筛选：为图分类构建可解释性GNN
Message-passing selection: Towards interpretable GNNs for graph classification
HTML
PDF
Wenda Li, Kaixuan Chen, Shunyu Liu, Wenjie Huang, Haofei Zhang...
TL;DR
本文介绍了一个名为MSInterpreter的可解释的GNN推理范例，提出了消息传递选择方案(MSScheme)来选定关键路径，旨在实现自解释而非事后解释，并在图分类基准测试中证明了方法的有效性。
Abstract
In this paper, we strive to develop an
interpretable gnns' inference
paradigm, termed
msinterpreter
, which can serve as a plug-and-play scheme readily applicable to various GNNs' baselines. Unlike the most existi
→