… To address all the abovementioned limitations, we present Graph Mamba Networks (…
Graph Mamba Networks (GMNs) as a new class of graph learning based on state space models. …

… 4 Related work on state-space models with graphs In this section, popular methods from
the literature related to graph-based state-space representations are reviewed and …

… dependent graphs and introduce GraphS4mer, a general graph neural … tasks by modeling
spatiotemporal dependencies in … graph classification and regression tasks, we focus on graph …

… To develop spatio-temporal models for fMRI data, we adopt the … state-space model S4 [24]
and extend it to a graph setting to fit the nature of the data. The S4 model can efficiently model …

… , we propose Graph State Space Network (GrassNet), a novel graph neural … graph spectral
filters. In particular, our GrassNet introduces structured state space models (SSMs) to model …

… of State Space Models (SSMs) to graphs. We propose Graph State Space Convolution (…
aggregation and factorizable graph kernels depending on relative graph distances. These …

… graph (STG) learning model named STGMamba that leverages modern selective state space
models (… -Decoder structure, with the Graph Selective State Space Block (GS3B) as basic …

… , a graph state space model for modeling the dynamics of temporal graphs. Extensive …
effectiveness of our GRAPHSSM framework across various temporal graph benchmarks. …

… of state-space models. The core concept of Graph Mamba is its state-space modeling approach,
… processing graph information by dynamically focusing on the most relevant parts of the …

… Inspired by the success of state space models, eg, Mamba, for efficiently capturing … modeling,
we propose DyG-Mamba, a new continuous state space model (SSM) for dynamic graph …