mlsanityData to 14 Oct 2026

DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs

arXiv 2408.06966 ↗First posted 13 Aug 2024cs.LGcited by 17

On the map: State-space sequence models (S4, Mamba) → Video, motion and generative Mamba models

Abstract (arXiv)

Dynamic graph modeling aims to uncover evolutionary patterns in real-world systems, enabling accurate social recommendation and early detection of cancer cells. Inspired by the success of recent state space models in efficiently capturing long-term dependencies, we propose DyG-Mamba by translating dynamic graph modeling into a long-term sequence modeling problem. Specifically, inspired by Ebbinghaus' forgetting curve, we treat the irregular timespans between events as control signals, allowing DyG-Mamba to dynamically adjust the forgetting of historical information. This mechanism ensures effective usage of irregular timespans, thereby improving both model effectiveness and inductive capability. In addition, inspired by Ebbinghaus' review cycle, we redefine core parameters to ensure that DyG-Mamba selectively reviews historical information and filters out noisy inputs, further enhancing the model's robustness. Through exhaustive experiments on 12 datasets covering dynamic link prediction and node classification tasks, we show that DyG-Mamba achieves state-of-the-art performance on most datasets, while demonstrating significantly improved computational and memory efficiency. Code is available at https://github.com/Clearloveyuan/DyG-Mamba.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 52 of its 80 references that are in the map. First posted on arXiv 13 Aug 2024.

Builds on

52 of 80 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model19 Mar
  2. 2024Graph Mamba: Towards Learning on Graphs with State Space Models13 Feb
  3. 2024Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces1 Feb

Other references · 49

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  4. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  5. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
  6. 2020Linformer: Self-Attention with Linear Complexitycited by 1,474
  7. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  8. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
  9. 2022Simplified State Space Layers for Sequence Modelingcited by 788
  10. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
  11. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 605
  12. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 530
37 more
  1. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
  2. 2022Hungry Hungry Hippos: Towards Language Modeling with State Space Modelscited by 499
  3. 2020Inductive Representation Learning on Temporal Graphscited by 462
  4. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 448
  5. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 447
  6. 2022Diagonal State Spaces are as Effective as Structured State Spacescited by 350
  7. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 275
  8. 2021Inductive Representation Learning in Temporal Networks via Causal Anonymous Walkscited by 193
  9. 2023Towards Better Dynamic Graph Learning: New Architecture and Unified Librarycited by 157
  10. 2023Do We Really Need Complicated Model Architectures For Temporal Networks?cited by 143
  11. 2024MambaOut: Do We Really Need Mamba for Vision?cited by 143
  12. 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 138
  13. 2022ROLAND: Graph Learning Framework for Dynamic Graphscited by 132
  14. 2022Towards Better Evaluation for Dynamic Link Predictioncited by 122
  15. 2019AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networkscited by 112
  16. 2024Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Taskscited by 105
  17. 2018Streaming Graph Neural Networkscited by 91
  18. 2020ConvBERT: Improving BERT with Span-based Dynamic Convolutioncited by 88
  19. 2021TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learningcited by 68
  20. 2020Learning Continuous System Dynamics from Irregularly-Sampled Partial Observationscited by 61
  21. 2021Dynamic Graph Neural Networks for Sequential Recommendationcited by 57
  22. 2019Memory Augmented Graph Neural Networks for Sequential Recommendationcited by 46
  23. 2024A Survey of Mambacited by 39
  24. 2024A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challengescited by 30
  25. 2023Deep Temporal Graph Clusteringcited by 28
  26. 2024Long Range Propagation on Continuous-Time Dynamic Graphscited by 28
  27. 2020Evolutionary dynamics of higher-order interactions in social networkscited by 26
  28. 2024A survey of dynamic graph neural networkscited by 24
  29. 2024On the Feasibility of Simple Transformer for Dynamic Graph Modelingcited by 22
  30. 2024State Space Models on Temporal Graphs: A First-Principles Studycited by 16
  31. 2022Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphscited by 13
  32. 2023RDGSL: Dynamic Graph Representation Learning with Structure Learningcited by 13
  33. 2022Piecewise-Velocity Model for Learning Continuous-time Dynamic Node Representationscited by 10
  34. 2023An Empirical Evaluation of Temporal Graph Benchmarkcited by 8
  35. 2022Continuous-Time User Preference Modelling for Temporal Sets Predictioncited by 7
  36. 2023Laplacian Change Point Detection for Single and Multi-view Dynamic Graphscited by 7
  37. 2024On the Generalization Capability of Temporal Graph Learning Algorithms: Theoretical Insights and a Simpler Methodcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 8.

17 papers.

Sort:

By area:

  1. 2024Best of Both Worlds: Advantages of Hybrid Graph Sequence Modelscited by 6
  2. 2025Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applicationscited by 6
  3. 2025DP-DGAD: A Generalist Dynamic Graph Anomaly Detector with Dynamic Prototypescited by 5
  4. 2025How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learningcited by 4
  5. 2024Exploring Graph Mamba: A Comprehensive Survey on State-Space Models for Graph Learningcited by 2
  6. 2025Integrating Sequential and Relational Modeling for User Events: Datasets and Prediction Taskscited by 1
  7. 2026Node Role-Guided LLMs for Dynamic Graph Clusteringcited by 1
  8. 2025GLADMamba: Unsupervised Graph-Level Anomaly Detection Powered by Selective State Space Modelcited by 0
  9. 2025DyGSSM: Multi-view Dynamic Graph Embeddings with State Space Model Gradient Updatecited by 0
  10. 2025Deltat-Mamba3D: A Time-Aware Spatio-Temporal State-Space Model for Breast Cancer Risk Predictioncited by 0
  11. 2026Distributionally Robust Set Representation Learning Under Inference-Time Element Corruptioncited by 0
  12. 2026Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Modelscited by 0
5 more
  1. 2026Temporal Sheaf Neural Networks with Dynamic Orthogonal Transportcited by 0
  2. 2026Long-Term Behavioral Evaluation for Trusted Collaborator Selection via Bidirectional Mambacited by 0
  3. 2026Beyond the Survey: A Systematic Empirical Study of Detection and Association in Visual MOTcited by 0
  4. 2026Your Temporal Link Predictor Is Blind to Who Is Active: A Missing Factor That Transfers Across Modelscited by 0
  5. 2026Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Contextcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models
  2. 2024DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models
  3. 2024A Comparative Study on Dynamic Graph Embedding based on Mamba and Transformers
  4. 2025Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling
  5. 2026Sequence Diffusion Model for Temporal Link Prediction in Continuous-Time Dynamic Graph
  6. 2025SourceDetMamba: A Graph-aware State Space Model for Source Detection in Sequential Hypergraphs
  7. 2024Retrieval Augmented Generation for Dynamic Graph Modeling
  8. 2026Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies