为均值聚合GNN提供可解释的逻辑规则，揭示其表达能力边界。
Sound Logical Explanations for Mean Aggregation Graph Neural Networks
- 基于非负权重的均值聚合GNN，构建可验证的单调逻辑规则
- 实验表明非负权重下性能相当或更优，且能生成有效解释
- 适合关注模型可解释性与可信推理的研究者
图神经网络（GNN）广泛用于知识图谱补全，但其黑箱特性限制了可信应用。尽管均值聚合在实践中普遍使用，相关可解释性与表达能力研究仍不足。本文研究带非负权重的均值聚合GNN（MAGNNs），精确刻画了其可被可靠解释的单调逻辑规则类别，并提出一类受限的一阶逻辑片段以解释任意MAGNN预测。实验表明，将均值聚合GNN限制为非负权重后，在标准归纳基准上性能相当或提升；实际中可获得可靠逻辑规则，生成有意义解释，并暴露训练模型中的潜在问题。
原文摘要 · Abstract (English)
Graph neural networks (GNNs) are frequently used for knowledge graph completion. Their black-box nature has motivated work that uses sound logical rules to explain predictions and characterise their expressivity. However, despite the prevalence of GNNs that use mean as an aggregation function, explainability and expressivity results are lacking for them. We consider GNNs with mean aggregation and non-negative weights (MAGNNs), proving the precise class of monotonic rules that can be sound for them, as well as providing a restricted fragment of first-order logic to explain any MAGNN prediction. Our experiments show that restricting mean-aggregation GNNs to have non-negative weights yields comparable or improved performance on standard inductive benchmarks, that sound rules are obtained in practice, that insightful explanations can be generated in practice, and that the sound rules can expose issues in the trained models.
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。