{"ID":2838917,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.16062","arxiv_id":"2511.16062","title":"Gauge-Equivariant Graph Networks via Self-Interference Cancellation","abstract":"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.","short_abstract":"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 projec...","url_abs":"https://arxiv.org/abs/2511.16062","url_pdf":"https://arxiv.org/pdf/2511.16062v2","authors":"[\"Yoonhyuk Choi\",\"Jiho Choi\",\"Jiwoo Kang\"]","published":"2025-11-20T05:48:22Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Graph Neural Network\"]","has_code":false,"code_links":[{"ID":606817,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2838917,"paper_url":"https://arxiv.org/abs/2511.16062","paper_title":"Gauge-Equivariant Graph Networks via Self-Interference Cancellation","repo_url":"https://github.com/ChoiYoonHyuk/GESC","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}