剖析图神经网络泛化能力，揭示结构与聚合对预测效果的影响
Covered Forest: Fine-grained generalization analysis of graph neural networks
- 基于图相似性理论分析结构与聚合机制的作用
- 实验证明模型在复杂图结构上的泛化性能差异
- 适合研究图神经网络泛化性的研究人员参考
消息传递图神经网络（MPNNs）的表达能力已通过图同构测试的组合技术得到较好理解。然而，其泛化能力——在训练集之外做出有意义预测的能力——仍缺乏深入探讨。现有泛化分析常忽略图结构，局限于特定聚合函数，并假设难以优化的0-1损失函数。本文利用图相似性理论的最新进展，评估图结构、聚合方式及损失函数对MPNN泛化能力的影响。实验结果支持理论发现，深化了对MPNN泛化特性的理解。
原文摘要 · Abstract (English)
The expressive power of message-passing graph neural networks (MPNNs) is reasonably well understood, primarily through combinatorial techniques from graph isomorphism testing. However, MPNNs' generalization abilities -- making meaningful predictions beyond the training set -- remain less explored. Current generalization analyses often overlook graph structure, limit the focus to specific aggregation functions, and assume the impractical, hard-to-optimize $0$-$1$ loss function. Here, we extend recent advances in graph similarity theory to assess the influence of graph structure, aggregation, and loss functions on MPNNs' generalization abilities. Our empirical study supports our theoretical insights, improving our understanding of MPNNs' generalization properties.
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。