mlsanityData to 7 Oct 2026

Exploring Time Granularity on Temporal Graphs for Dynamic Link Prediction in Real-world Networks

arXiv 2311.12255 ↗First posted 21 Nov 2023cs.LG cs.SIcited by 2

Not on the map. Why?

Abstract (arXiv)

Dynamic Graph Neural Networks (DGNNs) have emerged as the predominant approach for processing dynamic graph-structured data. However, the influence of temporal information on model performance and robustness remains insufficiently explored, particularly regarding how models address prediction tasks with different time granularities. In this paper, we explore the impact of time granularity when training DGNNs on dynamic graphs through extensive experiments. We examine graphs derived from various domains and compare three different DGNNs to the baseline model across four varied time granularities. We mainly consider the interplay between time granularities, model architectures, and negative sampling strategies to obtain general conclusions. Our results reveal that a sophisticated memory mechanism and proper time granularity are crucial for a DGNN to deliver competitive and robust performance in the dynamic link prediction task. We also discuss drawbacks in considered models and datasets and propose promising directions for future research on the time granularity of temporal graphs.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 25 of its 46 references that are in the map. First posted on arXiv 21 Nov 2023.

Builds on

25 of 46 references.

References · 25

  1. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 521
  2. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  3. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  4. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 443
  5. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 399
  6. 2019Representation Learning for Dynamic Graphs: A Surveycited by 260
  7. 2019Time2Vec: Learning a Vector Representation of Timecited by 208
  8. 2021Inductive Representation Learning in Temporal Networks via Causal Anonymous Walkscited by 188
  9. 2021A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directionscited by 144
  10. 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 137
  11. 2022ROLAND: Graph Learning Framework for Dynamic Graphscited by 131
  12. 2020Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A surveycited by 123
13 more
  1. 2022Towards Better Evaluation for Dynamic Link Predictioncited by 120
  2. 2018Streaming Graph Neural Networkscited by 91
  3. 2022Neighborhood-aware Scalable Temporal Network Representation Learningcited by 54
  4. 2019Self-attention with Functional Time Representation Learningcited by 52
  5. 2022TREND: TempoRal Event and Node Dynamics for Graph Representation Learningcited by 50
  6. 2018Dynamic Graph Representation Learning via Self-Attention Networkscited by 39
  7. 2021Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognitioncited by 25
  8. 2021DyGCN: Dynamic Graph Embedding with Graph Convolutional Networkcited by 6
  9. 2021DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Abilitycited by 5
  10. 2021Exploring Temporal Granularity in Self-Supervised Video Representation Learningcited by 5
  11. 2015Unwinding the hairball graph: pruning algorithms for weighted complex networkscited by 3
  12. 2022Who is next: rising star prediction via diffusion of user interest in social networkscited by 2
  13. 2021Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021cited by 1

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Relational Graph Transformercited by 30
  2. 2025A Survey of Link Prediction in Temporal Networkscited by 6