mlsanityData to 7 Oct 2026

Long Range Propagation on Continuous-Time Dynamic Graphs

arXiv 2406.02740 ↗First posted 4 Jun 2024cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

Learning Continuous-Time Dynamic Graphs (C-TDGs) requires accurately modeling spatio-temporal information on streams of irregularly sampled events. While many methods have been proposed recently, we find that most message passing-, recurrent- or self-attention-based methods perform poorly on long-range tasks. These tasks require correlating information that occurred "far" away from the current event, either spatially (higher-order node information) or along the time dimension (events occurred in the past). To address long-range dependencies, we introduce Continuous-Time Graph Anti-Symmetric Network (CTAN). Grounded within the ordinary differential equations framework, our method is designed for efficient propagation of information. In this paper, we show how CTAN's (i) long-range modeling capabilities are substantiated by theoretical findings and how (ii) its empirical performance on synthetic long-range benchmarks and real-world benchmarks is superior to other methods. Our results motivate CTAN's ability to propagate long-range information in C-TDGs as well as the inclusion of long-range tasks as part of temporal graph models evaluation.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 30 of its 46 references that are in the map. First posted on arXiv 4 Jun 2024.

Builds on

30 of 46 references.

References · 30

  1. 2018Neural Ordinary Differential Equationscited by 3,733
  2. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  3. 2019Simplifying Graph Convolutional Networkscited by 1,470
  4. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 624
  5. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 521
  6. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  7. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  8. 2020Inductive Representation Learning on Temporal Graphscited by 454
  9. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 443
  10. 2017Stable Architectures for Deep Neural Networkscited by 340
  11. 2019Representation Learning for Dynamic Graphs: A Surveycited by 260
  12. 2021GRAND: Graph Neural Diffusioncited by 258
18 more
  1. 2022Long Range Graph Benchmarkcited by 258
  2. 2023Towards Better Dynamic Graph Learning: New Architecture and Unified Librarycited by 154
  3. 2019Graph Neural Ordinary Differential Equationscited by 153
  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. 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
  7. 2022Graph-Coupled Oscillator Networkscited by 123
  8. 2022Towards Better Evaluation for Dynamic Link Predictioncited by 120
  9. 2019Fake News Detection on Social Media using Geometric Deep Learningcited by 115
  10. 2019A Gentle Introduction to Deep Learning for Graphscited by 107
  11. 2021PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equationscited by 106
  12. 2018Streaming Graph Neural Networkscited by 91
  13. 2021Dissecting the Diffusion Process in Linear Graph Convolutional Networkscited by 58
  14. 2022Anti-Symmetric DGN: a stable architecture for Deep Graph Networkscited by 58
  15. 2022Provably expressive temporal graph networkscited by 56
  16. 2022Scalable Spatiotemporal Graph Neural Networkscited by 52
  17. 2023Deep learning for dynamic graphs: models and benchmarkscited by 19
  18. 2023An Empirical Evaluation of Temporal Graph Benchmarkcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 15; 2026: 7.

26 papers.

Sort:

By area:

  1. 2025On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learningcited by 42
  2. 2024DyG-Mamba: Continuous State Space Modeling on Dynamic Graphscited by 15
  3. 2024DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Modelscited by 14
  4. 2025Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Taskscited by 12
  5. 2025Over-squashing in Spatiotemporal Graph Neural Networkscited by 6
  6. 2025Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamicscited by 6
  7. 2026Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspectivecited by 4
  8. 2025Unlocking Multi-Modal Potentials for Link Prediction on Dynamic Text-Attributed Graphscited by 3
  9. 2025Are We Really Measuring Progress? Transferring Insights from Evaluating Recommender Systems to Temporal Link Predictioncited by 2
  10. 2025Revisiting Node Affinity Prediction in Temporal Graphscited by 2
  11. 2024Expressivity of Representation Learning on Continuous-Time Dynamic Graphs: An Information-Flow Centric Reviewcited by 1
  12. 2025HyperEvent: A Strong Baseline for Dynamic Link Prediction via Relative Structural Encodingcited by 1
14 more
  1. 2025Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learningcited by 1
  2. 2025Integrating Sequential and Relational Modeling for User Events: Datasets and Prediction Taskscited by 1
  3. 2024Information propagation dynamics in Deep Graph Networkscited by 0
  4. 2025STX-Search: Explanation Search for Continuous Dynamic Spatio-Temporal Modelscited by 0
  5. 2025FLASH: Flexible Learning of Adaptive Sampling from History in Temporal Graph Neural Networkscited by 0
  6. 2025Trajectory Encoding Temporal Graph Networkscited by 0
  7. 2025Non-Dissipative Graph Propagation for Non-Local Community Detectioncited by 0
  8. 2025Graph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learningcited by 0
  9. 2026Kernelized Edge Attention: Addressing Semantic Attention Blurring in Temporal Graph Neural Networkscited by 0
  10. 2026TFWaveFormer: Temporal-Frequency Collaborative Multi-level Wavelet Transformer for Dynamic Link Predictioncited by 0
  11. 2026Time-varying Interaction Graph ODE for Dynamic Graph Representation Learningcited by 0
  12. 2026Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Modelscited by 0
  13. 2026Temporal Sheaf Neural Networks with Dynamic Orthogonal Transportcited by 0
  14. 2026Physics-Refined Spatiotemporal Forecasting on Open-Boundary Hydrologic Graphscited by 0