Entropy-Aware Time-Varying Graph Neural Networks with Generalized Temporal Hawkes Process: Dynamic Link Prediction in the Presence of Node Addition and Deletion
-
Published:2023-10-04
Issue:4
Volume:5
Page:1359-1381
-
ISSN:2504-4990
-
Container-title:Machine Learning and Knowledge Extraction
-
language:en
-
Short-container-title:MAKE
Author:
Najafi Bahareh12ORCID, Parsaeefard Saeedeh3, Leon-Garcia Alberto2ORCID
Affiliation:
1. Department of Computer Science, University of British Columbia, Vancouver, BC V6T 1Z2, Canada 2. Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON M5S 3G8, Canada 3. Apple Inc., San Francisco, CA 95014, USA
Abstract
This paper addresses the problem of learning temporal graph representations, which capture the changing nature of complex evolving networks. Existing approaches mainly focus on adding new nodes and edges to capture dynamic graph structures. However, to achieve more accurate representation of graph evolution, we consider both the addition and deletion of nodes and edges as events. These events occur at irregular time scales and are modeled using temporal point processes. Our goal is to learn the conditional intensity function of the temporal point process to investigate the influence of deletion events on node representation learning for link-level prediction. We incorporate network entropy, a measure of node and edge significance, to capture the effect of node deletion and edge removal in our framework. Additionally, we leveraged the characteristics of a generalized temporal Hawkes process, which considers the inhibitory effects of events where past occurrences can reduce future intensity. This framework enables dynamic representation learning by effectively modeling both addition and deletion events in the temporal graph. To evaluate our approach, we utilize autonomous system graphs, a family of inhomogeneous sparse graphs with instances of node and edge additions and deletions, in a link prediction task. By integrating these enhancements into our framework, we improve the accuracy of dynamic link prediction and enable better understanding of the dynamic evolution of complex networks.
Funder
Alberto Leon-Garcia’s University of Toronto operating grant
Subject
Artificial Intelligence,Engineering (miscellaneous)
Reference47 articles.
1. Thakur, N., and Han, C.Y. (2021). A study of fall detection in assisted living: Identifying and improving the optimal machine learning method. J. Sens. Actuator Netw., 10. 2. Bergamaschi, S., De Nardis, S., Martoglia, R., Ruozzi, F., Sala, L., Vanzini, M., and Vigliermo, R.A. (2022). Novel perspectives for the management of multilingual and multialphabetic heritages through automatic knowledge extraction: The digitalmaktaba approach. Sensors, 22. 3. Rizoiu, M.A., Xie, L., Sanner, S., Cebrian, M., Yu, H., and Van Hentenryck, P. (2017, January 3–7). Expecting to be hip: Hawkes intensity processes for social media popularity. Proceedings of the 26th International Conference on World Wide Web, Perth, Australia. 4. Rossi, E., Chamberlain, B., Frasca, F., Eynard, D., Monti, F., and Bronstein, M. (2020). Temporal graph networks for deep learning on dynamic graphs. arXiv. 5. Kumar, S., Zhang, X., and Leskovec, J. (2019, January 4–8). Predicting dynamic embedding trajectory in temporal interaction networks. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.
|
|