mlsanityData to 14 Oct 2026

On The Temporal Domain of Differential Equation Inspired Graph Neural Networks

arXiv 2401.11074 ↗First posted 20 Jan 2024cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have demonstrated remarkable success in modeling complex relationships in graph-structured data. A recent innovation in this field is the family of Differential Equation-Inspired Graph Neural Networks (DE-GNNs), which leverage principles from continuous dynamical systems to model information flow on graphs with built-in properties such as feature smoothing or preservation. However, existing DE-GNNs rely on first or second-order temporal dependencies. In this paper, we propose a neural extension to those pre-defined temporal dependencies. We show that our model, called TDE-GNN, can capture a wide range of temporal dynamics that go beyond typical first or second-order methods, and provide use cases where existing temporal models are challenged. We demonstrate the benefit of learning the temporal dependencies using our method rather than using pre-defined temporal dynamics on several graph benchmarks.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 47 of its 80 references that are in the map. First posted on arXiv 20 Jan 2024.

Builds on

47 of 80 references.

References · 47

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Graph Attention Networkscited by 8,923
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  7. 2018Neural Ordinary Differential Equationscited by 3,779
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  9. 2020Simple and Deep Graph Convolutional Networkscited by 860
  10. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  11. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 631
  12. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
35 more
  1. 2019Multi-scale Attributed Node Embeddingcited by 548
  2. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
  3. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 447
  4. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
  5. 2019Diffusion Improves Graph Learningcited by 414
  6. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 401
  7. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 362
  8. 2017Stable Architectures for Deep Neural Networkscited by 341
  9. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 311
  10. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 275
  11. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 261
  12. 2021GRAND: Graph Neural Diffusioncited by 258
  13. 2020A Note on Over-Smoothing for Graph Neural Networkscited by 249
  14. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 247
  15. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 214
  16. 2018Deep Neural Networks Motivated by Partial Differential Equationscited by 187
  17. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  18. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  19. 2019Graph Neural Ordinary Differential Equationscited by 154
  20. 2022Graph-Coupled Oscillator Networkscited by 124
  21. 2021PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Modelscited by 118
  22. 2021PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equationscited by 106
  23. 2023DRew: Dynamically Rewired Message Passing with Delaycited by 82
  24. 2021A Review on Graph Neural Network Methods in Financial Applicationscited by 78
  25. 2023Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunitiescited by 61
  26. 2022Anti-Symmetric DGN: a stable architecture for Deep Graph Networkscited by 60
  27. 2022Understanding convolution on graphs via energiescited by 59
  28. 2020A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecastingcited by 54
  29. 2022GREAD: Graph Neural Reaction-Diffusion Networkscited by 54
  30. 2023A Fractional Graph Laplacian Approach to Oversmoothingcited by 45
  31. 2019Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Featurescited by 31
  32. 2023Graph Neural Convection-Diffusion with Heterophilycited by 26
  33. 2019Dynamic Origin-Destination Matrix Prediction with Line Graph Neural Networks and Kalman Filtercited by 13
  34. 2018Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functionscited by 7
  35. 2022Learning time-dependent PDE solver using Message Passing Graph Neural Networkscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 2.

9 papers.

  1. 2025Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networkscited by 14
  2. 2024Temporal Graph ODEs for Irregularly-Sampled Time Seriescited by 11
  3. 2025Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modelingcited by 10
  4. 2024Distributed-Order Fractional Graph Operating Networkcited by 7
  5. 2025Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learningcited by 3
  6. 2025TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flowscited by 1
  7. 2024Information propagation dynamics in Deep Graph Networkscited by 0
  8. 2026Learning from Historical Activations in Graph Neural Networkscited by 0
  9. 2026A Critical Audit of Spatiotemporal Forecasting Benchmark Datasets and Modelscited by 0