Topological Deep Learning with State-Space Models: A Mamba Approach for Simplicial Complexes

TL;DR

This paper introduces a novel topological deep learning architecture using state-space models for simplicial complexes, enabling higher-order interactions beyond pairwise relations, and demonstrates its competitive performance.

Contribution

It proposes a new Mamba-based model for simplicial complexes that directly models higher-order interactions without message passing mechanisms.

Findings

Achieves competitive results on simplicial complex tasks.

Enables direct communication among higher-order structures.

Outperforms some existing models in accuracy and efficiency.

Abstract

Graph Neural Networks based on the message-passing (MP) mechanism are a dominant approach for handling graph-structured data. However, they are inherently limited to modeling only pairwise interactions, making it difficult to explicitly capture the complexity of systems with $n$-body relations. To address this, topological deep learning has emerged as a promising field for studying and modeling higher-order interactions using various topological domains, such as simplicial and cellular complexes. While these new domains provide powerful representations, they introduce new challenges, such as effectively modeling the interactions among higher-order structures through higher-order MP. Meanwhile, structured state-space sequence models have proven to be effective for sequence modeling and have recently been adapted for graph data by encoding the neighborhood of a node as a sequence, thereby avoiding the MP mechanism. In this work, we propose a novel architecture designed to operate with simplicial complexes, utilizing the Mamba state-space model as its backbone. Our approach generates sequences for the nodes based on the neighboring cells, enabling direct communication between all higher-order structures, regardless of their rank. We extensively validate our model, demonstrating that it achieves competitive performance compared to state-of-the-art models developed for simplicial complexes.