LogicXGNN: 基于逻辑规则的图神经网络解释方法
LogicXGNN: Grounded Logical Rules for Explaining Graph Neural Networks
AI总结：
LogicXGNN通过构建逻辑规则提升图神经网络解释的可信度和可解释性，提出数据驱动的 fidelity 指标并显著提升解释质量。
摘要：
现有基于规则的图神经网络解释方法提供全局可解释性，但往往在中间不可解释的概念空间中优化和评估保真度，忽略了最终子图解释中对终端用户的接地质量。为此，我们提出了 LogicXGNN，一个事后框架，通过在可靠谓词上构建逻辑规则，显式捕捉 GNN 的消息传递结构，从而确保有效的接地。我们进一步引入数据驱动的保真度（Fid_D），一个评估解释最终图形式的真实指标，以及覆盖度和有效性等互补效用指标。在广泛的实验中，LogicXGNN 相比最先进的方法在保真度上平均提高了超过 20%，且速度快 10-100 倍。凭借强大的可扩展性和效用性能，LogicXGNN 生成的解释忠实于模型的逻辑并可靠地基于可观测数据。我们的代码可在 https://github.com/allengeng123/LogicXGNN/ 上获取。
英文摘要：
Existing rule-based explanations for Graph Neural Networks (GNNs) provide global interpretability but often optimize and assess fidelity in an intermediate, uninterpretable concept space, overlooking grounding quality for end users in the final subgraph explanations. This gap yields explanations that may appear faithful yet be unreliable in practice. To this end, we propose LogicXGNN, a post-hoc framework that constructs logical rules over reliable predicates explicitly designed to capture the GNN's message-passing structure, thereby ensuring effective grounding. We further introduce data-grounded fidelity ($\textit{Fid}_{\mathcal{D}}$), a realistic metric that evaluates explanations in their final-graph form, along with complementary utility metrics such as coverage and validity. Across extensive experiments, LogicXGNN improves $\textit{Fid}_{\mathcal{D}}$ by over 20% on average relative to state-of-the-art methods while being 10-100 $\times$ faster. With strong scalability and utility performance, LogicXGNN produces explanations that are faithful to the model's logic and reliably grounded in observable data. Our code is available at https://github.com/allengeng123/LogicXGNN/.
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。
