Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Exploring Time Granularity on Temporal Graphs for Dynamic Link Prediction in Real-world Networks (2311.12255v2)

Published 21 Nov 2023 in cs.LG and cs.SI

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. Graph neural networks in recommender systems: a survey. ACM Computing Surveys, 55(5):1–37, 2022.
  2. A survey of graph neural networks for recommender systems: Challenges, methods, and directions. ACM Transactions on Recommender Systems, 1(1):1–51, 2023.
  3. Who’s next: Rising star prediction via diffusion of user interest in social networks. IEEE Transactions on Knowledge and Data Engineering, 2022.
  4. T-gcn: A temporal graph convolutional network for traffic prediction. IEEE transactions on intelligent transportation systems, 21(9):3848–3858, 2019.
  5. Spatial-temporal graph attention networks: A deep learning approach for traffic forecasting. IEEE Access, 7:166246–166256, 2019.
  6. Variational graph neural networks for road traffic prediction in intelligent transportation systems. IEEE Transactions on Industrial Informatics, 17(4):2802–2812, 2020.
  7. Causalgnn: Causal-based graph neural networks for spatio-temporal epidemic forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 30, pages 12191–12199, 2022.
  8. Ai techniques for forecasting epidemic dynamics: Theory and practice. In Artificial Intelligence in Covid-19, pages 193–228. Springer, 2022.
  9. Graph neural networks for temporal graphs: State of the art, open challenges, and opportunities, 2023-02-03.
  10. Learning multi-granular spatio-temporal graph network for skeleton-based action recognition. In Proceedings of the 29th ACM international conference on multimedia, pages 4334–4342, 2021.
  11. Foundations and modeling of dynamic networks using dynamic graph neural networks: A survey. IEEE Access, 9:79143–79168, 2021.
  12. Spatio-temporal deep learning method for adhd fmri classification. Information Sciences, 499:1–11, 2019.
  13. Efficient residential load forecasting using deep learning approach. International Journal of Computer Applications in Technology, 68(3):205–214, 2022.
  14. Exploring temporal granularity in self-supervised video representation learning. arXiv preprint arXiv:2112.04480, 2021.
  15. Representation learning for dynamic graphs: A survey. The Journal of Machine Learning Research, 21(1):2648–2720, 2020.
  16. Transferable knowledge-based multi-granularity fusion network for weakly supervised temporal action detection. IEEE Transactions on Multimedia, 23:1503–1515, 2020.
  17. Transferable knowledge-based multi-granularity aggregation network for temporal action localization: Submission to activitynet challenge 2021. arXiv preprint arXiv:2107.12618, 2021.
  18. Temporal graph networks for deep learning on dynamic graphs. arXiv preprint arXiv:2006.10637, 2020.
  19. Predicting dynamic embedding trajectory in temporal interaction networks. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pages 1269–1278, 2019.
  20. Inductive representation learning in temporal networks via causal anonymous walks. arXiv preprint arXiv:2101.05974, 2021.
  21. Towards better evaluation for dynamic link prediction, 2022-09-11.
  22. Representation learning for dynamic graphs: A survey, 2020-04-27.
  23. Foundations and modelling of dynamic networks using dynamic graph neural networks: A survey. IEEE Access, 9:79143–79168, 2021.
  24. Streaming graph neural networks, 2018.
  25. Evolvegcn: Evolving graph convolutional networks for dynamic graphs, 2019.
  26. Inductive representation learning in temporal networks via causal anonymous walks, 2022.
  27. TemporalGAT: Attention-based dynamic graph representation learning. In Hady W. Lauw, Raymond Chi-Wing Wong, Alexandros Ntoulas, Ee-Peng Lim, See-Kiong Ng, and Sinno Jialin Pan, editors, Advances in Knowledge Discovery and Data Mining, Lecture Notes in Computer Science, pages 413–423. Springer International Publishing, 2020.
  28. Dynamic graph representation learning via self-attention networks, 2019.
  29. DySAT: Deep neural representation learning on dynamic graphs via self-attention networks. In Proceedings of the 13th International Conference on Web Search and Data Mining, WSDM ’20, pages 519–527. Association for Computing Machinery, 2020-01-22.
  30. Dyformer: A scalable dynamic graph transformer with provable benefits on generalization ability, 2023.
  31. Dygcn: Dynamic graph embedding with graph convolutional network, 2021.
  32. Time Granularity, pages 59–118. Foundations of Artificial Intelligence. Elsevier, 2005. ffhal-00922282.
  33. Temporal graph benchmark for machine learning on temporal graphs. arXiv preprint arXiv:2307.01026, 2023.
  34. Temporal networks. Physics Reports, 519(3):97–125, 2012-10.
  35. Expressivity of time-varying graphs. In Leszek Gąsieniec and Frank Wolter, editors, Fundamentals of Computation Theory, volume 8070, pages 95–106. Springer Berlin Heidelberg, 2013. Series Title: Lecture Notes in Computer Science.
  36. Continuous-time dynamic network embeddings. In Companion Proceedings of the The Web Conference 2018, WWW ’18, page 969–976, Republic and Canton of Geneva, CHE, 2018. International World Wide Web Conferences Steering Committee.
  37. Time2vec: Learning a vector representation of time, 2019.
  38. Self-attention with functional time representation learning, 2019.
  39. Area under the receiver operating characteristic curve. Applied Logistic Regression. Third ed: Wiley, pages 173–182, 2013.
  40. Dyrep: Learning representations over dynamic graphs. In International Conference on Learning Representations, 2019.
  41. Untangling the hairballs of multi-centered, small-world online social media networks. Journal of Graph Algorithms and Applications: JGAA, 19(2):595–618, 2015.
  42. Visone. https://visone.ethz.ch/, 2011. Accessed on: March 23, 2023.
  43. Cambridge Intelligence. Introducing the powerful organic graph layout. https://cambridge-intelligence.com/introducing-the-powerful-organic-graph-layout/, 2021. [Accessed: March 24, 2023].
  44. yed graph editor. https://www.yworks.com/products/yed, 2023. Accessed on: March 23, 2023.
  45. Navid Dianati. Unwinding the hairball graph: Pruning algorithms for weighted complex networks. Phys. Rev. E, 93:012304, Jan 2016.
  46. Trend: Temporal event and node dynamics for graph representation learning. In Proceedings of the ACM Web Conference 2022, pages 1159–1169, 2022.
  47. Neighborhood-aware scalable temporal network representation learning. In Learning on Graphs Conference, pages 1–1. PMLR, 2022.
  48. Roland: Graph learning framework for dynamic graphs. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’22, page 2358–2366, New York, NY, USA, 2022. Association for Computing Machinery.
  49. The enron email dataset database schema and brief statistical report. Information sciences institute technical report, University of Southern California, 4(1):120–128, 2004.
  50. Sensing the" health state" of a community. IEEE Pervasive Computing, 11(4):36–45, 2011.
  51. Patterns and dynamics of users’ behavior and interaction: Network analysis of an online community. Journal of the American Society for Information Science and Technology, 60(5):911–932, 2009.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now