Explaining Identity-aware Graph Classifiers through the Language of Motifs.

IJCNN(2023)

引用 0|浏览26
暂无评分
摘要
Most methods for explaining black-box classifiers (e.g., on tabular data, images, or time series) rely on measuring the impact that removing/perturbing features has on the model output. This forces the explanation language to match the classifier's feature space. However, when dealing with graph data, in which the basic features correspond to the edges describing the graph structure, this matching between features space and explanation language might not be appropriate. Decoupling the feature space (edges) from a desired high-lever explanation language (such as motifs) is thus a major challenge towards developing actionable explanations for graph classification tasks. In this paper we introduce GRAPHSHAP, a Shapley-based approach able to provide motif-based explanations for identity-aware graph classifiers, assuming no knowledge whatsoever about the model or its training data: the only requirement is that the classifier can be queried as a black-box at will. For the sake of computational efficiency we explore a progressive approximation strategy and show how a simple kernel can efficiently approximate explanation scores, thus allowing GRAPHSHAP to scale on scenarios with a large explanation space (i.e., large number of motifs). We showcase GRAPHSHAP on a real-world brain-network dataset consisting of patients affected by Autism Spectrum Disorder and a control group. Our experiments highlight how the classification provided by a black-box model can be effectively explained by few connectomics patterns.
更多
查看译文
关键词
actionable explanations,black-box classifiers,black-box model,classifier,explaining identity-aware graph classifiers,explanation scores,explanation space,feature space,features space,graph classification tasks,graph data,graph structure,Graphshap,high-lever explanation language,identityaware graph classifiers,model output,motif-based explanations,motifs,Shapley-based approach,tabular data,time series,training data
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要