mlsanityData to 13 Oct 2026

Expressivity of Representation Learning on Continuous-Time Dynamic Graphs: An Information-Flow Centric Review

arXiv 2412.03783 ↗First posted 5 Dec 2024cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Graphs are ubiquitous in real-world applications, ranging from social networks to biological systems, and have inspired the development of Graph Neural Networks (GNNs) for learning expressive representations. While most research has centered on static graphs, many real-world scenarios involve dynamic, temporally evolving graphs, motivating the need for Continuous-Time Dynamic Graph (CTDG) models. This paper provides a comprehensive review of Graph Representation Learning (GRL) on CTDGs with a focus on Self-Supervised Representation Learning (SSRL). We introduce a novel theoretical framework that analyzes the expressivity of CTDG models through an Information-Flow (IF) lens, quantifying their ability to propagate and encode temporal and structural information. Leveraging this framework, we categorize existing CTDG methods based on their suitability for different graph types and application scenarios. Within the same scope, we examine the design of SSRL methods tailored to CTDGs, such as predictive and contrastive approaches, highlighting their potential to mitigate the reliance on labeled data. Empirical evaluations on synthetic and real-world datasets validate our theoretical insights, demonstrating the strengths and limitations of various methods across long-range, bi-partite and community-based graphs. This work offers both a theoretical foundation and practical guidance for selecting and developing CTDG models, advancing the understanding of GRL in dynamic settings.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 35 of its 49 references that are in the map. First posted on arXiv 5 Dec 2024.

Builds on

35 of 49 references.

References · 35

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
  3. 2017Graph Attention Networkscited by 8,888
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,364
  5. 2018How Powerful are Graph Neural Networks?cited by 4,373
  6. 2021On the Opportunities and Risks of Foundation Modelscited by 3,999
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,471
  8. 2016node2vec: Scalable Feature Learning for Networkscited by 1,915
  9. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 958
  10. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  11. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 629
  12. 2019Self-labelling via simultaneous clustering and representation learningcited by 526
23 more
  1. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 525
  2. 2020Inductive Representation Learning on Temporal Graphscited by 457
  3. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 445
  4. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 413
  5. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  6. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 274
  7. 2019Representation Learning for Dynamic Graphs: A Surveycited by 262
  8. 2022Long Range Graph Benchmarkcited by 261
  9. 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
  10. 2023Do We Really Need Complicated Model Architectures For Temporal Networks?cited by 142
  11. 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 137
  12. 2018Streaming Graph Neural Networkscited by 91
  13. 2023DRew: Dynamically Rewired Message Passing with Delaycited by 82
  14. 2022Provably expressive temporal graph networkscited by 56
  15. 2020A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecastingcited by 54
  16. 2016Deep Coevolutionary Network: Embedding User and Item Features for Recommendationcited by 33
  17. 2024Long Range Propagation on Continuous-Time Dynamic Graphscited by 27
  18. 2022A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learningcited by 24
  19. 2024On the Feasibility of Simple Transformer for Dynamic Graph Modelingcited by 22
  20. 2023Deep learning for dynamic graphs: models and benchmarkscited by 19
  21. 2024PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networkscited by 10
  22. 2021Self-Supervised Dynamic Graph Representation Learning via Temporal Subgraph Contrastcited by 5
  23. 2024Temporal Graph Rewiring with Expander Graphscited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Revisiting Node Affinity Prediction in Temporal Graphscited by 2