提出双通道图神经网络，解决自解释模型解释力不足的问题。
Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective
- 用形式化方法分析现有自解释GNN的解释机制
- 发现其解释常不如完备解释且与可信性不一致
- 引入白盒规则提取器增强解释能力，适合需要可靠解释的场景
自解释图神经网络（SE-GNN）是可解释设计的主流方法，但其解释特性与局限性尚不明确。本文首次形式化了若干流行SE-GNN的解释，称为最小解释（MEs），并与经典解释概念（如最小蕴含项PI和忠实解释）进行比较。分析表明，MEs在特定任务族中等价于PI解释，但在一般情况下信息量低于PI解释，且与广泛接受的忠实性标准存在显著偏差。尽管忠实解释和PI解释更具信息量，但其求解通常不可行且规模可能过大。为此，本文提出双通道GNN，集成白盒规则提取器与标准SE-GNN，动态融合两种解释路径。实验显示，即使简单实现，该模型也能恢复简洁规则，并在性能上达到或超过主流SE-GNN。
原文摘要 · Abstract (English)
Self-Explainable Graph Neural Networks (SE-GNNs) are popular explainable-by-design GNNs, but their explanations' properties and limitations are not well understood. Our first contribution fills this gap by formalizing the explanations extracted by some popular SE-GNNs, referred to as Minimal Explanations (MEs), and comparing them to established notions of explanations, namely Prime Implicant (PI) and faithful explanations. Our analysis reveals that MEs match PI explanations for a restricted but significant family of tasks. In general, however, they can be less informative than PI explanations and are surprisingly misaligned with widely accepted notions of faithfulness. Although faithful and PI explanations are informative, they are intractable to find and we show that they can be prohibitively large. Given these observations, a natural choice is to augment SE-GNNs with alternative modalities of explanations taking care of SE-GNNs' limitations. To this end, we propose Dual-Channel GNNs that integrate a white-box rule extractor and a standard SE-GNN, adaptively combining both channels. Our experiments show that even a simple instantiation of Dual-Channel GNNs can recover succinct rules and perform on par or better than widely used SE-GNNs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。