Pith. sign in

REVIEW 23 cited by

Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.00789 v1 pith:6ZDMEA3Q submitted 2024-02-01 cs.LG cs.AI

Chloe Wang , Oleksii Tsepa , Jun Ma , Bo Wang This is my paper · ORCID
classification cs.LGcs.AI
keywords graphlong-rangegraph-mambaattentioncomputationalmodelingcontextcost
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Attention mechanisms have been widely used to capture long-range dependencies among nodes in Graph Transformers. Bottlenecked by the quadratic computational cost, attention mechanisms fail to scale in large graphs. Recent improvements in computational efficiency are mainly achieved by attention sparsification with random or heuristic-based graph subsampling, which falls short in data-dependent context reasoning. State space models (SSMs), such as Mamba, have gained prominence for their effectiveness and efficiency in modeling long-range dependencies in sequential data. However, adapting SSMs to non-sequential graph data presents a notable challenge. In this work, we introduce Graph-Mamba, the first attempt to enhance long-range context modeling in graph networks by integrating a Mamba block with the input-dependent node selection mechanism. Specifically, we formulate graph-centric node prioritization and permutation strategies to enhance context-aware reasoning, leading to a substantial improvement in predictive performance. Extensive experiments on ten benchmark datasets demonstrate that Graph-Mamba outperforms state-of-the-art methods in long-range graph prediction tasks, with a fraction of the computational cost in both FLOPs and GPU memory consumption. The code and models are publicly available at https://github.com/bowang-lab/Graph-Mamba.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 23 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approach

    cs.LG 2025-02 conditional novelty 7.0 of 10

    A simplified selective state-space layer expresses polynomials whose degree grows with sequence length, exceeding the fixed per-layer degree of linear attention.

  2. Benchmarking Sheaf Neural Networks for Inductive Tasks

    cs.LG 2026-08 conditional novelty 6.0 of 10

    On 14 inductive graph benchmarks, sheaf neural networks underperform strong GNN baselines, and their performance is driven more by the surrounding architecture than by the sheaf diffusion mechanism.

  3. Navigating Hierarchy: Hyperbolic Learning on Brain Graphs for Disorder Diagnosis

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A hyperbolic-space framework with geometric entailment constraints and a graph-aware Mamba module improves brain-network classification of ASD and MDD by explicitly modeling ROI-to-community-to-whole-brain hierarchy.

  4. eMamba: Efficient Acceleration Framework for Mamba Models in Edge Computing

    cs.LG 2025-08 conditional novelty 6.0 of 10

    An end-to-end Mamba edge accelerator using hardware-friendly approximations, INT8 quantization, and NAS achieves 4.95x-5.62x lower latency and 1.63x-19.9x smaller models than ViT/CNN baselines.

  5. TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows

    cs.LG 2025-08 conditional novelty 6.0 of 10

    TANGO adds a learnable energy gradient and an orthogonal tangential flow to GNN layers, improving long-range and heterophilic graph benchmarks.

  6. Mamba-X: An End-to-End Vision Mamba Accelerator for Edge Computing Devices

    cs.AR 2025-08 conditional novelty 6.0 of 10

    A dedicated accelerator for Vision Mamba using a Kogge-Stone systolic scan array and hybrid 8-bit quantization achieves 2.3x end-to-end speedup and 11.5x energy-efficiency gain over an edge GPU with less than 1% top-1...

  7. On Measuring Long-Range Interactions in Graph Neural Networks

    cs.LG 2025-06 conditional novelty 6.0 of 10

    The paper axiomatizes a distance-weighted influence measure of range and uses it to show that LRGB tasks differ sharply in how long-range they really are.

  8. A Physics-Augmented GraphGPS Framework for the Reconstruction of 3D Riemann Problems from Sparse Data

    physics.flu-dyn 2025-05 conditional novelty 6.0 of 10

    A graph transformer with shock-aware attention and guided message-passing reconstructs 3D Riemann problem flows from 10% observed points more accurately than the benchmark ML models tested.

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

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A message-passing GNN based on a linear recurrence plus MLP readout achieves strong results on long-range, heterophilic, and spatio-temporal graph benchmarks.

  10. From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics

    cs.LG 2025-02 conditional novelty 6.0 of 10

    S6LA adds a selective state space recurrence across the layers of CNNs and vision transformers, giving consistent accuracy gains on ImageNet classification and COCO detection and segmentation.

  11. GRAMA: Adaptive Graph Autoregressive Moving Average Models

    cs.LG 2025-01 conditional novelty 6.0 of 10

    GRAMA is a graph-adaptive ARMA architecture that wraps GNN backbones with selective sequential recurrences and reports consistent gains on long-range graph benchmarks.

  12. BrainMAP: Learning Multiple Activation Pathways in Brain Networks

    cs.AI 2024-12 conditional novelty 6.0 of 10

    BrainMAP adaptively sequences brain-region graphs, routes them through a Mixture of Experts of Mamba models, and achieves state-of-the-art results on five HCP fMRI benchmarks with saliency-based explanations.

  13. Efficient Self-Supervised Video Hashing with Selective State Spaces

    cs.CV 2024-12 conditional novelty 6.0 of 10

    S5VH uses bidirectional Mamba layers and a hash-center alignment loss to improve self-supervised video hashing accuracy and efficiency.

  14. ReHub: Linear Complexity Graph Transformers with Adaptive Hub-Spoke Reassignment

    cs.LG 2024-12 conditional novelty 6.0 of 10

    ReHub keeps spoke-to-hub attention sparse by connecting each node to only k hubs per layer and reassigning those hubs via hub-hub similarity, reaching O(N) complexity with accuracy on par with its dense variant.

  15. Best of Both Worlds: Advantages of Hybrid Graph Sequence Models

    cs.LG 2024-11 conditional novelty 6.0 of 10

    A hybrid graph sequence model with HAC-based hierarchical tokenization and a Mamba-plus-Transformer encoder outperforms prior graph transformers and recurrent baselines on most tested benchmarks.

  16. DiM-Gestor: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2

    cs.SD 2024-11 conditional novelty 6.0 of 10

    DiM-Gestor generates co-speech 3D gestures from Chinese speech using a Mamba-2 and AdaLN diffusion architecture, and releases the CCG dataset.

  17. HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A state space model based point cloud network with shuffled Hilbert serialization, a convolutional bidirectional S6 branch, and multi-head S6 achieves new top scores on ModelNet40, ShapeNet, S3DIS, and ScanObjectNN.

  18. MambaHash: Visual State Space Deep Hashing Model for Large-Scale Image Retrieval

    cs.CV 2025-06 conditional novelty 5.0 of 10

    MambaHash uses a grouped, multi-directional Mamba backbone for deep supervised hashing and reports the highest mean average precision on CIFAR-10 and IMAGENET, with marginal gains on NUS-WIDE.

  19. MV-GMN: State Space Model for Multi-View Action Recognition

    cs.CV 2025-01 conditional novelty 5.0 of 10

    MV-GMN, a state-space model with graph convolution, reports state-of-the-art accuracies on NTU RGB+D and PKU-MMD action recognition benchmarks.

  20. MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights

    cs.LG 2024-12 conditional novelty 5.0 of 10

    MOL-Mamba combines Mamba state-space layers, graph neural networks, and electronic descriptors to improve molecular property prediction on 8 of 11 MoleculeNet benchmarks.

  21. DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models

    cs.LG 2024-12 conditional novelty 5.0 of 10

    DG-Mamba combines Mamba state space models, kernelized attention, and a Principle of Relevant Information regularizer to learn robust dynamic graph structures in linear time.

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

    cs.LG 2024-12 conditional novelty 2.0 of 10

    A survey of Graph Mamba, the adaptation of state-space models (Mamba, S4, S6) to graph learning, synthesizing roughly 30 recent papers into a taxonomy of architectures, applications, benchmarks, and open challenges.

  23. Deep Learning-based Approaches for State Space Models: A Selective Review

    stat.ML 2024-12 conditional novelty 1.0 of 10

    A selective review that unifies classical and deep learning state space models, from latent neural ODEs/SDEs to structured SSM architectures like S4 and Mamba.

Pith tools