Exploring Graph Mamba: A Comprehensive Survey on State-Space Models for Graph Learning

TL;DR

Graph Mamba integrates state-space models with graph learning to achieve long-range dependency modeling at near-linear complexity, addressing core GNN limitations. The survey systematically unpacks the architecture, selective scanning, and spatial-temporal processing, and surveys variants, applications, and benchmarks across diverse domains. It highlights notable contributions such as GSSC, GMN, HeteGraph-Mamba, and STG-Mamba, while candidly outlining challenges in scalability, interpretability, and training convergence. The work emphasizes practical impact in domains from traffic forecasting and healthcare to remote sensing and finance, and calls for advances in SSL, dynamic graphs, and cross-domain integration to unlock Graph Mamba’s full potential.

Abstract

Graph Mamba, a powerful graph embedding technique, has emerged as a cornerstone in various domains, including bioinformatics, social networks, and recommendation systems. This survey represents the first comprehensive study devoted to Graph Mamba, to address the critical gaps in understanding its applications, challenges, and future potential. We start by offering a detailed explanation of the original Graph Mamba architecture, highlighting its key components and underlying mechanisms. Subsequently, we explore the most recent modifications and enhancements proposed to improve its performance and applicability. To demonstrate the versatility of Graph Mamba, we examine its applications across diverse domains. A comparative analysis of Graph Mamba and its variants is conducted to shed light on their unique characteristics and potential use cases. Furthermore, we identify potential areas where Graph Mamba can be applied in the future, highlighting its potential to revolutionize data analysis in these fields. Finally, we address the current limitations and open research questions associated with Graph Mamba. By acknowledging these challenges, we aim to stimulate further research and development in this promising area. This survey serves as a valuable resource for both newcomers and experienced researchers seeking to understand and leverage the power of Graph Mamba.

Figures (2)

• Figure 1: Graph Mamba Architecture: including sequence transformations (Conv and SSM blocks), linear projections, and non-linearity through activation and multiplication operations.
• Figure 2: Illustration of different graph types analyzed with the Graph Mamba Framework.