GNNAnatomy：重新思考图神经网络的模型级解释
GNNAnatomy: Rethinking Model-Level Explanations for Graph Neural Networks
AI总结：
本文提出基于蒸馏的GNNAnatomy，利用graphlet表示和透明MLP代理提取多粒度模型级解释，并通过人机协同接口增强可信度。
摘要：
图神经网络（GNN）在基于图的任务中取得了卓越性能，但仍然难以解释。本文重新审视了GNN模型级解释方法背后的基础性假设，即：（1）最大化分类置信度可产生具有代表性的解释；（2）单一解释足以覆盖整个图类别；（3）解释本身天然可信。我们指出了这些假设导致的陷阱：优化分类置信度的方法可能忽略被部分学习的模式；同一类别内不同图子集之间的拓扑多样性往往未被充分呈现；而当解释应用于新数据集或模型时，仅凭解释对建立用户信任的支持有限。本文提出GNNAnatomy，这是一种基于蒸馏的方法，旨在生成解释并避免上述陷阱。GNNAnatomy首先使用graphlets（一组基础子结构）刻画图拓扑。随后，我们训练一个透明的多层感知机代理模型，使其基于graphlet表示直接逼近GNN预测。通过分析分配给每个graphlet的权重，我们识别出最具判别力的拓扑，并将其作为GNN解释。为了考虑类别内部的结构多样性，GNNAnatomy通过支持人机协同的接口，按所需粒度生成解释。该接口帮助用户识别由不同关键子结构驱动类别区分的图子集，从而实现多粒度解释。此外，通过支持探索并将解释关联回输入图，该接口增强了透明度和信任。我们在合成数据集和真实世界数据集上，通过定量指标以及与最先进的模型级可解释GNN方法的定性比较，对GNNAnatomy进行了评估。
英文摘要：
Graph Neural Networks (GNNs) achieve outstanding performance across graph-based tasks but remain difficult to interpret. In this paper, we revisit foundational assumptions underlying model-level explanation methods for GNNs, namely: (1) maximizing classification confidence yields representative explanations, (2) a single explanation suffices for an entire class of graphs, and (3) explanations are inherently trustworthy. We identify pitfalls resulting from these assumptions: methods that optimize for classification confidence may overlook partially learned patterns; topological diversity across graph subsets within the same class is often underrepresented; and explanations alone offer limited support for building user trust when applied to new datasets or models. This paper introduces GNNAnatomy, a distillation-based method designed to generate explanations while avoiding these pitfalls. GNNAnatomy first characterizes graph topology using graphlets, a set of fundamental substructures. We then train a transparent multilayer perceptron surrogate to directly approximate GNN predictions based on the graphlet representations. By analyzing the weights assigned to each graphlet, we identify the most discriminative topologies, which serve as GNN explanations. To account for structural diversity within a class, GNNAnatomy generates explanations at the required granularity through an interface that supports human-AI teaming. This interface helps users identify subsets of graphs where distinct critical substructures drive class differentiation, enabling multi-grained explanations. Additionally, by enabling exploration and linking explanations back to input graphs, the interface fosters greater transparency and trust. We evaluate GNNAnatomy on both synthetic and real-world datasets through quantitative metrics and qualitative comparisons with state-of-the-art model-level explainable GNN methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
