paper-with-me

Papers

Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling

2025-05-24 · Andrea Ceni, Alessio Gravina, Claudio Gallicchio, Davide Bacciu, Carola-Bibiane Schonlieb, Moshe Eliasof

The recent success of State-Space Models (SSMs) in sequence modeling has motivated their adaptation to graph learning, giving rise to Graph State-Space Models (GSSMs). However, existing GSSMs operate by applying SSM modules to sequences extracted from graphs, often compromising core properties such as permutation equivariance, message-passing compatibility, and computational efficiency. In this paper, we introduce a new perspective by embedding the key principles of modern SSM computation directly into the Message-Passing Neural Network framework, resulting in a unified methodology for both static and temporal graphs. Our approach, MP-SSM, enables efficient, permutation-equivariant, and long-range information propagation while preserving the architectural simplicity of message passing. Crucially, MP-SSM enables an exact sensitivity analysis, which we use to theoretically characterize information flow and evaluate issues like vanishing gradients and over-squashing in the deep regime. Furthermore, our design choices allow for a highly optimized parallel implementation akin to modern SSMs. We validate MP-SSM across a wide range of tasks, including node classification, graph property prediction, long-range benchmarks, and spatiotemporal forecasting, demonstrating both its versatility and strong empirical performance.

📄 PDF Abstract BibTeX arXiv:2505.18728

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyGraph LearningGraph Property PredictionNode ClassificationProperty PredictionState Space Models

Similar Papers 제목 키워드 기반

Rethinking Graph Neural Architecture Search from Message-passing

2021-03-26 · CVPR 2021 1 · Shaofei Cai, Liang Li, Jincan Deng, Beichen Zhang 외

Graph neural networks (GNNs) emerged recently as a standard toolkit for learning from data on graphs. Current GNN designing works depend on immense human expertise to explore different message-passing mechanisms, and req…

feature selectionNeural Architecture Search

From Message-Passing to Linearized Graph Sequence Models

2026-05-12 · Joël Mathys, Basil Rohner, Saku Peltonen, Roger Wattenhofer arxiv

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 sequenc…

Graph Learning

DPGNN: Dual-Perception Graph Neural Network for Representation Learning

2021-10-15 · Li Zhou, Wenyu Chen, Dingyi Zeng, Shaohuan Cheng 외

Graph neural networks (GNNs) have drawn increasing attention in recent years and achieved remarkable performance in many graph-based tasks, especially in semi-supervised learning on graphs. However, most existing GNNs ar…

Graph Neural NetworkGraph Representation LearningRepresentation Learning

Towards Dynamic Message Passing on Graphs

2024-10-31 · Junshu Sun, Chenxue Yang, Xiangyang Ji, Qingming Huang 외

Message passing plays a vital role in graph neural networks (GNNs) for effective feature learning. However, the over-reliance on input topology diminishes the efficacy of message passing and restricts the ability of GNNs…

Graph Classification

Deep Message Passing on Sets

2019-09-21 · Yifeng Shi, Junier Oliva, Marc Niethammer

Modern methods for learning over graph input data have shown the fruitfulness of accounting for relationships among elements in a collection. However, most methods that learn over set input data use only rudimentary appr…

DenoisingRelational Reasoning