Quantifying the Intrinsic Usefulness of Attributional Explanations for Graph Neural Networks with Artificial Simulatability Studies
CoRR(2023)
摘要
Despite the increasing relevance of explainable AI, assessing the quality of
explanations remains a challenging issue. Due to the high costs associated with
human-subject experiments, various proxy metrics are often used to
approximately quantify explanation quality. Generally, one possible
interpretation of the quality of an explanation is its inherent value for
teaching a related concept to a student. In this work, we extend artificial
simulatability studies to the domain of graph neural networks. Instead of
costly human trials, we use explanation-supervisable graph neural networks to
perform simulatability studies to quantify the inherent usefulness of
attributional graph explanations. We perform an extensive ablation study to
investigate the conditions under which the proposed analyses are most
meaningful. We additionally validate our methods applicability on real-world
graph classification and regression datasets. We find that relevant
explanations can significantly boost the sample efficiency of graph neural
networks and analyze the robustness towards noise and bias in the explanations.
We believe that the notion of usefulness obtained from our proposed
simulatability analysis provides a dimension of explanation quality that is
largely orthogonal to the common practice of faithfulness and has great
potential to expand the toolbox of explanation quality assessments,
specifically for graph explanations.
更多查看译文
关键词
attributional explanations,graph neural networks,neural networks
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要