Position-Aware and Subgraph Enhanced Dynamic Graph Contrastive Learning on Discrete-Time Dynamic Graph
Source abstract
Abstract
Unsupervised learning methods such as graph contrastive learning have been used for dynamic graph representation learning to eliminate the dependence of labels. However, existing studies neglect positional information when le... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Graph Neural Networks · Text and Document Classification Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (21)
Show source-provided references
1. Combine temporal information in session-based recommendation with graph neural networks10.1016/j.eswa.2023.121969 ↗
2. W. Kong, Z. Guo, and Y. Liu, “Spatio-temporal pivotal graph neural networks for traffic flow forecasting,” presented at the 38th AAAI Conf. Artif. Intell. (AAAI), Vancouver, BC, Canada, Feb. 20–27, 2024, pp. 8627–8635. doi: 10.1609/aaai.v38i8.28707.10.1609/aaai.v38i8.28707 ↗
3. H. Chen, P. Jiao, H. Tang, and H. Wu, “Temporal graph representation learning with adaptive augmentation contrastive,” presented at the Joint Eur. Conf. Mach. Learn. Knowl. Discov. Databases (ECML PKDD), Turin, Italy, Sep. 18–22, 2023, pp. 683–699. doi: 10.1007/978-3-031-43415-0_40.10.1007/978-3-031-43415-0_40 ↗
4. DyTSCL: Dynamic graph representation via tempo-structural contrastive learning
5. Dynamic graph contrastive learning via maximize temporal consistency10.1016/j.patcog.2023.110144 ↗
6. Scalable temporal latent space inference for link prediction in dynamic social networks10.1109/TKDE.2016.2591009 ↗
7. D. Rafailidis and A. Nanopoulos, “Modeling the dynamics of user preferences in coupled tensor factorization,” presented at the ACM Conf. Recomm. Syst. (RecSys), Silicon Valley, CA, USA, Oct. 6–10, 2014, pp. 321–324. doi: 10.1145/2645710.2645758.10.1145/2645710.2645758 ↗
8. S. D. Winter, T. Decuypere, S. Mitrović, B. Baesens, and J. D. Weerdt, “Combining temporal aspects of dynamic networks with Node2Vec for a more efficient dynamic link prediction,” presented at the IEEE/ACM Int. Conf. Adv. Soc. Netw. Anal. Min. (ASONAM), Barcelona, Spain, Aug. 28–31, 2018, pp. 1234–1241. doi: 10.1109/asonam.2018.8508272.10.1109/ASONAM.2018.8508272 ↗
9. S. Mahdavi, S. Khoshraftar, and A. An, “dynnode2vec: Scalable dynamic network embeddingScalable dynamic network embedding,” presented at the IEEE Int. Conf. Big Data (Big Data), Seattle, WA, USA, Dec. 10–13, 2018, pp. 3762–3765. doi: 10.1109/bigdata.2018.8621910.10.1109/BigData.2018.8621910 ↗
10. A. Pareja et al., “EvolveGCN: Evolving graph convolutional networks for dynamic graphs,” presented at the AAAI Conf. Artif. Intell. (AAAI), New York, NY, USA, Feb. 7–12, 2020, pp. 5363–5370. doi: 10.1609/aaai.v34i04.5984.10.1609/aaai.v34i04.5984 ↗
11. M. Yang, M. Zhou, M. Kalander, Z. Huang, and I. King, “Discrete-time temporal network embedding via implicit hierarchical learning in hyperbolic space,” presented at the 27th ACM SIGKDD Conf. Knowl. Discov. Data Min. (KDD), Singapore, Aug. 14–18, 2021, pp. 1975–1985. doi: 10.1145/3447548.3467422.10.1145/3447548.3467422 ↗
12. Q. Bai, C. Nie, H. Zhang, D. Zhao, and X. Yuan, “HGWaveNet: A hyperbolic graph neural network for temporal link prediction,” presented at the ACM Web Conf. 2023 (WWW), Austin, TX, USA, Apr. 30–May 4, 2023, pp. 523–532. doi: 10.1145/3543507.3583455.10.1145/3543507.3583455 ↗
13. H. Li, Z. Zhang, D. Liang, and Y. Jiang, “K-Truss based temporal graph convolutional network for dynamic graphs,” presented at the Asian Conf. Mach. Learn. (ACML), Hanoi, Vietnam, Dec. 5–8, 2024, pp. 739–754.
14. J. Li et al., “Scaling up dynamic graph representation learning via spiking neural networks,” presented at the 37th AAAI Conf. Artif. Intell. (AAAI), Washington, DC, USA, Feb. 7–13, 2023, pp. 8588–8596. doi: 10.1609/aaai.v37i7.26034.10.1609/aaai.v37i7.26034 ↗
15. N. Yin et al., “Dynamic spiking graph neural networks,” presented at the 38th AAAI Conf. Artif. Intell. (AAAI), Vancouver, BC, Canada, Feb. 20–27, 2024, pp. 16495–16503. doi: 10.1609/aaai.v38i15.29587.10.1609/aaai.v38i15.29587 ↗
16. X. Qin, N. Sheikh, C. Lei, B. Reinwald, and G. Domeniconi, “SEIGN: A simple and efficient graph neural network for large dynamic graphs,” presented at the 39th Int. Conf. Data Eng. (ICDE), Anaheim, CA, USA, Apr. 3–7, 2023, pp. 2850–2863. doi: 10.1109/icde55515.2023.00218.10.1109/ICDE55515.2023.00218 ↗
17. K. Zhao and L. Zhang, “Causality-inspired spatial-temporal explanations for dynamic graph neural networks,” presented at the 12th Int. Conf. Learn. Represent. (ICLR), Vienna, Austria, May. 7–11, 2024.
18. J. Chen and G. Kou, “Attribute and structure preserving graph contrastive learning,” presented at the 37th AAAI Conf. Artif. Intell. (AAAI), Washington, DC, USA, Feb. 7–13, 2023, pp. 7024–7032. doi: 10.1609/aaai.v37i6.25858.10.1609/aaai.v37i6.25858 ↗
19. T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, “A simple framework for contrastive learning of visual representations,” presented at the 37th Int. Conf. Mach. Learn. (ICML), Vienna, Austria, Jul. 13–18, 2020, pp. 1597–1607. doi: 10.48550/arXiv.2002.05709.
20. M. Liu and Y. Liu, “Inductive representation learning in temporal networks via mining neighborhood and community influences,” presented at the Int. ACM SIGIR Conf. Res. Dev. Inf. Retr. (SIGIR), Canada, Jul. 11–15, 2021, pp. 2202–2206. doi: 10.1145/3404835.3463052.10.1145/3404835.3463052 ↗
21. D. Xu, C. Ruan, E. Korpeoglu, S. Kumar, and K. Achan, “Inductive representation learning on temporal graphs,” presented at the 8th Int. Conf. Learn. Represent. (ICLR), Addis Ababa, Ethiopia, Apr. 26–30, 2020. doi: 10.48550/arXiv.2002.07962.