让图神经网络在使用节点标识时保持排列等变性，提升泛化能力。
On the Utilization of Unique Node Identifiers in Graph Neural Networks
- 通过对比损失正则化，使带唯一标识的图模型保持排列等变性。
- 在BREC基准上达到当前最佳性能，且训练收敛更快。
- 适合关注模型泛化与可解释性的图学习研究者。
图神经网络因消息传递结构存在固有的表征局限。近期研究表明，使用唯一节点标识符（UID）可克服这些局限。然而，我们指出其缺点在于丧失了排列等变性这一理想性质。为此，我们聚焦于保持排列等变性的UID模型，并提出理论论证其优势。受此启发，我们设计一种基于对比损失的正则化方法，引导UID模型趋向排列等变性。实验表明，该方法显著提升模型泛化与外推能力，同时加快训练收敛速度。在最新的BREC可表达性基准测试中，我们的方法优于其他基于随机性的现有方法，达到当前最优表现。
原文摘要 · Abstract (English)
Graph Neural Networks have inherent representational limitations due to their message-passing structure. Recent work has suggested that these limitations can be overcome by using unique node identifiers (UIDs). Here we argue that despite the advantages of UIDs, one of their disadvantages is that they lose the desirable property of permutation-equivariance. We thus propose to focus on UID models that are permutation-equivariant, and present theoretical arguments for their advantages. Motivated by this, we propose a method to regularize UID models towards permutation equivariance, via a contrastive loss. We empirically demonstrate that our approach improves generalization and extrapolation abilities while providing faster training convergence. On the recent BREC expressiveness benchmark, our proposed method achieves state-of-the-art performance compared to other random-based approaches.
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。