mlsanityData to 7 Oct 2026

Temporal Graph Networks for Deep Learning on Dynamic Graphs

arXiv 2006.10637 ↗First posted 18 Jun 2020cs.LG stat.MLcited by 521

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have recently become increasingly popular due to their ability to learn complex systems of relations or interactions arising in a broad spectrum of problems ranging from biology and particle physics to social networks and recommendation systems. Despite the plethora of different models for deep learning on graphs, few approaches have been proposed thus far for dealing with graphs that present some sort of dynamic nature (e.g. evolving features or connectivity over time). In this paper, we present Temporal Graph Networks (TGNs), a generic, efficient framework for deep learning on dynamic graphs represented as sequences of timed events. Thanks to a novel combination of memory modules and graph-based operators, TGNs are able to significantly outperform previous approaches being at the same time more computationally efficient. We furthermore show that several previous models for learning on dynamic graphs can be cast as specific instances of our framework. We perform a detailed ablation study of different components of our framework and devise the best configuration that achieves state-of-the-art performance on several transductive and inductive prediction tasks for dynamic graphs.

Key facts. Cited by 521 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 41; 2022: 64; 2023: 90; 2024: 103; 2025: 108; 2026: 115.

521 papers.

Sort:

By area:

  1. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  2. 2021Inductive Representation Learning in Temporal Networks via Causal Anonymous Walkscited by 188
  3. 2023Towards Better Dynamic Graph Learning: New Architecture and Unified Librarycited by 154
  4. 2023Do We Really Need Complicated Model Architectures For Temporal Networks?cited by 141
  5. 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 137
  6. 2022ROLAND: Graph Learning Framework for Dynamic Graphscited by 131
  7. 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
  8. 2022Towards Better Evaluation for Dynamic Link Predictioncited by 120
  9. 2022AEGNN: Asynchronous Event-based Graph Neural Networkscited by 118
  10. 2021Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphscited by 109
  11. 2021Combinatorial Optimization with Physics-Inspired Graph Neural Networkscited by 107
  12. 2021Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networkscited by 93
38 more
  1. 2021Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attentioncited by 86
  2. 2021Graph Representation Learning in Biomedicinecited by 79
  3. 2022A Survey on Graph Representation Learning Methodscited by 66
  4. 2021TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learningcited by 65
  5. 2023Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunitiescited by 60
  6. 2022TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphscited by 59
  7. 2022Provably expressive temporal graph networkscited by 56
  8. 2023Locality-Aware Graph-Rewiring in GNNscited by 55
  9. 2023Relational Deep Learning: Graph Representation Learning on Relational Databasescited by 55
  10. 2022Neighborhood-aware Scalable Temporal Network Representation Learningcited by 54
  11. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  12. 2023LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?cited by 40
  13. 2024TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphscited by 35
  14. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 34
  15. 2023Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoderscited by 32
  16. 2024A Survey of Deep Learning and Foundation Models for Time Series Forecastingcited by 32
  17. 2024LiGNN: Graph Neural Networks at LinkedIncited by 31
  18. 2023Kairos: Practical Intrusion Detection and Investigation using Whole-system Provenancecited by 30
  19. 2021Constructing Neural Network-Based Models for Simulating Dynamical Systemscited by 29
  20. 2022Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Modelscited by 29
  21. 2024A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challengescited by 29
  22. 2023Deep Temporal Graph Clusteringcited by 28
  23. 2022EvoKG: Jointly Modeling Event Time and Network Structure for Reasoning over Temporal Knowledge Graphscited by 27
  24. 2023TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discoverycited by 27
  25. 2021Noether Networks: Meta-Learning Useful Conserved Quantitiescited by 26
  26. 2023Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalizationcited by 26
  27. 2024Long Range Propagation on Continuous-Time Dynamic Graphscited by 26
  28. 2024DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphscited by 26
  29. 2022Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networkscited by 24
  30. 2022A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learningcited by 24
  31. 2023A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applicationscited by 22
  32. 2023Data-centric Graph Learning: A Surveycited by 22
  33. 2022Graph Neural Networks Designed for Different Graph Types: A Surveycited by 21
  34. 2022Scalable algorithms for physics-informed neural and graph networkscited by 21
  35. 2024A survey of dynamic graph neural networkscited by 21
  36. 2024Improving Temporal Link Prediction via Temporal Walk Matrix Projectioncited by 21
  37. 2023Deep learning for dynamic graphs: models and benchmarkscited by 19
  38. 2024Spectral Invariant Learning for Dynamic Graphs under Distribution Shiftscited by 18

50 most cited of 521 All 521 (JSON)