mlsanityData to 14 Oct 2026

Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context

arXiv 2610.19364 ↗First posted 14 Oct 2026cs.LGcited by 0

On the map: World models → World models for language agents also fits: Latent predictive world models

Abstract (arXiv)

Dynamic graph learning models how entities and their relations evolve from historical observations to predict future graph states. Existing methods do not fully address dynamic graph world modelling, which requires learning transitions from temporal context to future latent graph states. This is difficult for three reasons: nodes and relations rely on different historical evidence, structural evolution is path-dependent, and future snapshots provide sparse and realization-specific targets. We propose Dynamic Graph World Modelling (DyG-WM), the first framework to jointly predict future node and relation representations from temporal context by answering three questions: what has evolved, how it evolved, and what will evolve next. To capture what has evolved, a historical node-relation context encoder summarizes node-neighborhood trajectories and pair-specific histories. To characterize how it evolved, a node-relation path-signature encoder captures ordered structural changes. To predict what will evolve next, a dual-level joint-embedding objective predicts target-snapshot node and relation representations without reconstructing the raw graph. Experiments on 12 link-prediction and two node-classification datasets demonstrate the effectiveness of DyG-WM across both tasks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 33 of its 42 references that are in the map. First posted on arXiv 14 Oct 2026.

Builds on

33 of 42 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Graph World Models: Concepts, Taxonomy, and Future Directions30 Apr
  2. 2025Graph World Model14 Jul
  3. 2020Causal World Models by Unsupervised Deconfounding of Physical Dynamics28 Dec

Other references · 30

  1. 2018World Modelscited by 1,513
  2. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  3. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 530
  4. 2020Inductive Representation Learning on Temporal Graphscited by 462
  5. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 448
  6. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 447
  7. 2019Contrastive Learning of Structured World Modelscited by 209
  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. 2022ROLAND: Graph Learning Framework for Dynamic Graphscited by 132
  12. 2020Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A surveycited by 124
18 more
  1. 2022Towards Better Evaluation for Dynamic Link Predictioncited by 122
  2. 2016A Primer on the Signature Method in Machine Learningcited by 104
  3. 2020Improving Generative Imagination in Object-Centric World Modelscited by 71
  4. 2020World Model as a Graph: Learning Latent Landmarks for Planningcited by 69
  5. 2021TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learningcited by 68
  6. 2020Visual Grounding of Learned Physical Modelscited by 55
  7. 2019Temporal Network Embedding with Micro- and Macro-dynamicscited by 52
  8. 2024A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challengescited by 30
  9. 2024Long Range Propagation on Continuous-Time Dynamic Graphscited by 28
  10. 2023Embedding in Recommender Systems: A Surveycited by 20
  11. 2024DyG-Mamba: Continuous State Space Modeling on Dynamic Graphscited by 17
  12. 2024CLDG: Contrastive Learning on Dynamic Graphscited by 13
  13. 2022Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learningcited by 12
  14. 2024SiGNN: A Spike-induced Graph Neural Network for Dynamic Graph Representation Learningcited by 8
  15. 2025DP-DGAD: A Generalist Dynamic Graph Anomaly Detector with Dynamic Prototypescited by 5
  16. 2025Modeling Item-Level Dynamic Variability with Residual Diffusion for Bundle Recommendationcited by 2
  17. 2026Meta Dynamic Graph for Traffic Flow Predictioncited by 2
  18. 2026Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026WorldGraph: Graph-Native World Modeling
  2. 2026Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies
  3. 2024DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models
  4. 2026Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models
  5. 2025DyGSSM: Multi-view Dynamic Graph Embeddings with State Space Model Gradient Update
  6. 2026Node Role-Guided LLMs for Dynamic Graph Clustering
  7. 2025T-GRAB: A Synthetic Diagnostic Benchmark for Learning on Temporal Graphs
  8. 2025Global-Recent Semantic Reasoning on Dynamic Text-Attributed Graphs with Large Language Models