用扩散距离引导的优化框架，解决图神经网络过平滑问题
Rethinking Message Passing Neural Networks with Diffusion Distance-guided Stress Majorization
- 基于应力优化与正交约束构建新消息传递机制
- 在同质和异质图上均超越15个基线模型
- 适合研究图神经网络泛化能力的学者
过去十年中，消息传递神经网络（MPNNs）已成为图结构数据学习的主流模型。尽管有效，但多数模型仍存在过平滑和过度相关等问题，根源在于其最小化狄利克雷能量的目标及由此产生的邻域聚合操作。本文提出DDSM，一种基于应力主化与正交正则化的优化框架的新MPNN模型，并引入节点间的扩散距离以指导消息传递，开发了高效的距离近似算法，均有严格理论支持。大量实验表明，DDSM在同质与异质图上均显著优于15个强基线模型。
原文摘要 · Abstract (English)
Message passing neural networks (MPNNs) have emerged as go-to models for learning on graph-structured data in the past decade. Despite their effectiveness, most of such models still incur severe issues such as over-smoothing and -correlation, due to their underlying objective of minimizing the Dirichlet energy and the derived neighborhood aggregation operations. In this paper, we propose the DDSM, a new MPNN model built on an optimization framework that includes the stress majorization and orthogonal regularization for overcoming the above issues. Further, we introduce the diffusion distances for nodes into the framework to guide the new message passing operations and develop efficient algorithms for distance approximations, both backed by rigorous theoretical analyses. Our comprehensive experiments showcase that DDSM consistently and considerably outperforms 15 strong baselines on both homophilic and heterophilic graphs.
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。