mlsanityData to 14 Oct 2026

Towards Better Evaluation for Dynamic Link Prediction

arXiv 2207.10128 ↗First posted 20 Jul 2022cs.LG cs.SIcited by 122

Not on the map. Why?

Abstract (arXiv)

Despite the prevalence of recent success in learning from static graphs, learning from time-evolving graphs remains an open challenge. In this work, we design new, more stringent evaluation procedures for link prediction specific to dynamic graphs, which reflect real-world considerations, to better compare the strengths and weaknesses of methods. First, we create two visualization techniques to understand the reoccurring patterns of edges over time and show that many edges reoccur at later time steps. Based on this observation, we propose a pure memorization baseline called EdgeBank. EdgeBank achieves surprisingly strong performance across multiple settings because easy negative edges are often used in the current evaluation setting. To evaluate against more difficult negative edges, we introduce two more challenging negative sampling strategies that improve robustness and better match real-world applications. Lastly, we introduce six new dynamic graph datasets from a diverse set of domains missing from current benchmarks, providing new challenges and opportunities for future research. Our code repository is accessible at https://github.com/fpour/DGB.git.

Key facts. Cited by 122 papers in the map (data through 14 Oct 2026). Builds on 19 of its 65 references that are in the map. First posted on arXiv 20 Jul 2022.

Builds on

19 of 65 references.

References · 19

  1. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  2. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  3. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  4. 2020Benchmarking Graph Neural Networkscited by 680
  5. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 530
  6. 2020Inductive Representation Learning on Temporal Graphscited by 462
  7. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 448
  8. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 329
  9. 2019Representation Learning for Dynamic Graphs: A Surveycited by 265
  10. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  11. 2021Inductive Representation Learning in Temporal Networks via Causal Anonymous Walkscited by 193
  12. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
7 more
  1. 2021Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Spacecited by 67
  2. 2020Understanding Negative Sampling in Graph Representation Learningcited by 66
  3. 2015Evaluating Link Prediction Methodscited by 31
  4. 2020Laplacian Change Point Detection for Dynamic Graphscited by 25
  5. 2017Analysis of the Impact of Negative Sampling on Link Prediction in Knowledge Graphscited by 23
  6. 2016Evaluating Link Prediction Accuracy on Dynamic Networks with Added and Removed Edgescited by 8
  7. 2018Leveraging Friendship Networks for Dynamic Link Prediction in Social Interaction Networkscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 24; 2024: 38; 2025: 29; 2026: 31.

122 papers.

Sort:

By area:

  1. 2023Towards Better Dynamic Graph Learning: New Architecture and Unified Librarycited by 157
  2. 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 138
  3. 2024TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphscited by 36
  4. 2024A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challengescited by 30
  5. 2024Long Range Propagation on Continuous-Time Dynamic Graphscited by 28
  6. 2023TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discoverycited by 27
  7. 2024DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphscited by 27
  8. 2024A survey of dynamic graph neural networkscited by 24
  9. 2024Improving Temporal Link Prediction via Temporal Walk Matrix Projectioncited by 21
  10. 2023Deep learning for dynamic graphs: models and benchmarkscited by 19
  11. 2024Efficient Neural Common Neighbor for Temporal Graph Link Predictioncited by 18
  12. 2023TIGER: Temporal Interaction Graph Embedding with Restartscited by 17
38 more
  1. 2024DyG-Mamba: Continuous State Space Modeling on Dynamic Graphscited by 17
  2. 2024History repeats Itself: A Baseline for Temporal Knowledge Graph Forecastingcited by 15
  3. 2024Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient Transformationcited by 15
  4. 2025TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamicscited by 15
  5. 2024DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Modelscited by 14
  6. 2023DistTGL: Distributed Memory-Based Temporal Graph Neural Network Trainingcited by 12
  7. 2024MSPipe: Efficient Temporal GNN Training via Staleness-Aware Pipelinecited by 12
  8. 2024Repeat-Aware Neighbor Sampling for Dynamic Graph Learningcited by 11
  9. 2023Live Graph Lab: Towards Open, Dynamic and Real Transaction Graphs with NFTcited by 10
  10. 2023HOT: Higher-Order Dynamic Graph Representation Learning with Efficient Transformerscited by 10
  11. 2024UTG: Towards a Unified View of Snapshot and Event Based Models for Temporal Graphscited by 10
  12. 2023TransformerG2G: Adaptive time-stepping for learning temporal graph embeddings using transformerscited by 9
  13. 2023BenchTemp: A General Benchmark for Evaluating Temporal Graph Neural Networkscited by 9
  14. 2023An Empirical Evaluation of Temporal Graph Benchmarkcited by 8
  15. 2024Towards Adaptive Neighborhood for Advancing Temporal Interaction Graph Modelingcited by 8
  16. 2024Enhancing Cross-domain Link Prediction via Evolution Process Modelingcited by 7
  17. 2023Time-aware Graph Structure Learning via Sequence Prediction on Temporal Graphscited by 6
  18. 2024Supra-Laplacian Encoding for Transformer on Dynamic Graphscited by 6
  19. 2023Temporal graph models fail to capture global temporal dynamicscited by 5
  20. 2024Retrofitting Temporal Graph Neural Networks with Transformercited by 5
  21. 2024Temporal-Aware Evaluation and Learning for Temporal Graph Neural Networkscited by 5
  22. 2025Future Link Prediction Without Memory or Aggregationcited by 5
  23. 2023The Predicted-Updates Dynamic Model: Offline, Incremental, and Decremental to Fully Dynamic Transformationscited by 4
  24. 2023Continuous-time Graph Representation with Sequential Survival Processcited by 4
  25. 2024Learning-Based Link Anomaly Detection in Continuous-Time Dynamic Graphscited by 4
  26. 2025A Survey on Temporal Interaction Graph Representation Learning: Progress, Challenges, and Opportunitiescited by 4
  27. 2025What Do Temporal Graph Learning Models Learn?cited by 4
  28. 2026Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspectivecited by 4
  29. 2024Gaussian Embedding of Temporal Networkscited by 3
  30. 2024From Link Prediction to Forecasting: Addressing Challenges in Batch-based Temporal Graph Learningcited by 3
  31. 2024A Deep Probabilistic Framework for Continuous Time Dynamic Graph Generationcited by 3
  32. 2025Are Large Language Models Good Temporal Graph Learners?cited by 3
  33. 2025Learnable Spatial-Temporal Positional Encoding for Link Predictioncited by 3
  34. 2025Base3: a simple interpolation-based ensemble method for robust dynamic link predictioncited by 3
  35. 2025TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphscited by 3
  36. 2023Leveraging Temporal Graph Networks Using Module Decouplingcited by 2
  37. 2023Exploring Time Granularity on Temporal Graphs for Dynamic Link Prediction in Real-world Networkscited by 2
  38. 2024MTRGL:Effective Temporal Correlation Discerning through Multi-modal Temporal Relational Graph Learningcited by 2

50 most cited of 122 All 122 (JSON)