mlsanityData to 7 Oct 2026

Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations

arXiv 2302.11354 ↗First posted 22 Feb 2023cs.LG cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

This paper focuses on representation learning for dynamic graphs with temporal interactions. A fundamental issue is that both the graph structure and the nodes own their own dynamics, and their blending induces intractable complexity in the temporal evolution over graphs. Drawing inspiration from the recent progress of physical dynamic models in deep neural networks, we propose Graph Neural Controlled Differential Equations (GN-CDEs), a continuous-time framework that jointly models node embeddings and structural dynamics by incorporating a graph enhanced neural network vector field with a time-varying graph path as the control signal. Our framework exhibits several desirable characteristics, including the ability to express dynamics on evolving graphs without piecewise integration, the capability to calibrate trajectories with subsequent data, and robustness to missing observations. Empirical evaluation on a range of dynamic graph representation learning tasks demonstrates the effectiveness of our proposed approach in capturing the complex dynamics of dynamic graphs.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 33 of its 62 references that are in the map. First posted on arXiv 22 Feb 2023.

Builds on

33 of 62 references.

References · 33

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  6. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  7. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  8. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  9. 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
  10. 2019Graph Neural Networks for Social Recommendationcited by 711
  11. 2015LINE: Large-scale Information Network Embeddingcited by 582
  12. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 521
21 more
  1. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  2. 2020Inductive Representation Learning on Temporal Graphscited by 454
  3. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  4. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 443
  5. 2019Representation Learning for Dynamic Graphs: A Surveycited by 260
  6. 2021Inductive Representation Learning in Temporal Networks via Causal Anonymous Walkscited by 188
  7. 2021Graph Neural Controlled Differential Equations for Traffic Forecastingcited by 133
  8. 2019Continuous Graph Neural Networkscited by 114
  9. 2021MagNet: A Neural Network for Directed Graphscited by 104
  10. 2018DynGEM: Deep Embedding Method for Dynamic Graphscited by 100
  11. 2018Streaming Graph Neural Networkscited by 91
  12. 2021Graph Neural Networks in Network Neurosciencecited by 91
  13. 2020Directed Graph Convolutional Networkcited by 73
  14. 2021TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learningcited by 65
  15. 2018MotifNet: a motif-based Graph Convolutional Network for directed graphscited by 63
  16. 2020Streaming Graph Neural Networks via Continual Learningcited by 63
  17. 2019Neural Dynamics on Complex Networkscited by 38
  18. 2022Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecastingcited by 14
  19. 2021Efficient Dynamic Graph Representation Learning at Scalecited by 8
  20. 2021Continuous-Depth Neural Models for Dynamic Graph Predictioncited by 7
  21. 2021ConTIG: Continuous Representation Learning on Temporal Interaction Graphscited by 5

Built on by

Cited by year (2026 to 7 Oct)

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

7 papers.

  1. 2025Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Modelscited by 16
  2. 2025Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networkscited by 14
  3. 2025Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learningcited by 3
  4. 2025Graph Representation Learning with Diffusion Generative Modelscited by 2
  5. 2026Universal Time Series Generation with Neural Controlled Differential Equationscited by 0
  6. 2026Faithful Embeddings of Irregular and Asynchronous Data for Online Log-NCDEscited by 0
  7. 2026INDEQS: Informed Neural controlled Differential EQuationScited by 0