用符号规则替代消息传递，让图神经网络更高效可解释
Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning
- 用离散结构哈希和拓扑角色聚合取代传统消息传递
- 突破1-WL表达力瓶颈，训练速度提升10至100倍
- 生成语义精细的可解释规则，适合科学发现与可信AI
图神经网络（GNN）在药物发现等高风险领域至关重要，但其黑箱特性阻碍了可信度。现有自解释GNN多依赖继承局限的消息传递架构，存在1-魏斯费勒-莱曼（1-WL）表达力瓶颈且缺乏细粒度可解释性。为此，我们提出SymGraph，一种符号化框架，通过用离散结构哈希和基于拓扑角色的聚合替代连续消息传递，理论上超越1-WL限制，在无需可微优化开销的情况下实现更强表达力。大量实证评估表明，SymGraph达到当前最优性能，显著优于已有自解释GNN。尤为突出的是，其仅用CPU即可实现10至100倍的训练加速。此外，相比现有基于规则的方法，SymGraph生成的规则具备更优语义粒度，为科学发现与可解释人工智能提供巨大潜力。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have become essential in high-stakes domains such as drug discovery, yet their black-box nature remains a significant barrier to trustworthiness. While self-explainable GNNs attempt to bridge this gap, they often rely on standard message-passing backbones that inherit fundamental limitations, including the 1-Weisfeiler-Lehman (1-WL) expressivity barrier and a lack of fine-grained interpretability. To address these challenges, we propose SymGraph, a symbolic framework designed to transcend these constraints. By replacing continuous message passing with discrete structural hashing and topological role-based aggregation, our architecture theoretically surpasses the 1-WL barrier, achieving superior expressiveness without the overhead of differentiable optimization. Extensive empirical evaluations demonstrate that SymGraph achieves state-of-the-art performance, outperforming existing self-explainable GNNs. Notably, SymGraph delivers 10x to 100x speedups in training time using only CPU execution. Furthermore, SymGraph generates rules with superior semantic granularity compared to existing rule-based methods, offering great potential for scientific discovery and explainable AI.
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。