Abstract:Message-passing based approaches form the default backbone of most learning architectures on graph-structured data. However, the rapid progress of modern deep learning architectures in other domains, particularly sequence modeling, raises the question of how graph learning can benefit from these advances. We introduce Linearized Graph Sequence Models, a framework that recasts message-passing graph computation from the perspective of sequence modeling to simplify architectural choices. Our approach systematically separates the computational processing depth from the information propagation depth, allowing core graph architectural decisions to be treated as sequence modeling choices. Specifically, we analyze, both empirically and theoretically, what sequence properties make methods effective for learning and preserving the graph inductive bias. In particular, we validate our findings, demonstrating improved performance on long-range information tasks in graphs. Our findings provide a principled way to integrate modern sequence modeling advances into message-passing based graph learning. Beyond this, our work demonstrates how the separation of processing and information depth can recast central architectural questions as input modeling choices.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.12358 [cs.LG] |
| (or arXiv:2605.12358v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.12358 arXiv-issued DOI via DataCite (pending registration) |
From: Joël Mathys [view email]
[v1]
Tue, 12 May 2026 16:32:04 UTC (638 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。