提出GESC模型解决图神经网络在异质图上过平滑问题
Gauge-Equivariant Graph Networks via Self-Interference Cancellation
- 用投影机制替代传统加法聚合，抑制自干扰信号
- 在多个图数据集上超越现有最优模型性能
- 适合研究图神经网络消息传递机制的学者
图神经网络（GNN）在同质图上表现优异，但在异质图上常因自强化和相位不一致信号而失效。本文提出一种基于自干扰消除的规范等变图网络（GESC），将传统的加法聚合替换为基于投影的干扰机制。与以往依赖加法消息混合的磁性或规范等变GNN不同，GESC显式建模由冗余低频成分引起的自干扰。我们证明，现有规范基GNN缺乏干扰处理是导致规范传输下过平滑的主要原因。GESC引入一个U(1)相位连接后接秩1投影，以抑制注意力前的自平行分量，并设计符号感知门控机制调节负向对齐邻居。在多个多样化图基准测试中，GESC始终优于近期最先进模型，同时提供统一的、具备干扰感知的消息传递视角。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) excel on homophilous graphs but often fail under heterophily due to self-reinforcing and phase-inconsistent signals. We propose a \textbf{G}auge-\textbf{E}quivariant Graph Network with \textbf{S}elf-Interference \textbf{C}ancellation (GESC), which replaces additive aggregation with a projection-based interference mechanism. Unlike prior magnetic or gauge-equivariant GNNs that rely on additive message mixing, GESC explicitly models self-interference arising from redundant low-frequency components. We show that the absence of interference handling in existing gauge-based GNNs is a primary driver of oversmoothing under gauge transport. We introduce a $\mathrm{U}(1)$ phase connection followed by a rank-1 projection that suppresses self-parallel components before attention, and a sign-aware gate that regulates negatively aligned neighbors. Across diverse graph benchmarks, GESC consistently outperforms recent state-of-the-art models while offering a unified, interference-aware view of message passing. Our code is available at https://github.com/ChoiYoonHyuk/GESC.
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。