LIPIcs.TIME.2023.19.pdf
- Filesize: 0.5 MB
- 3 pages
Document
Time-Aware Robustness of Temporal Graph Neural Networks for Link Prediction (Extended Abstract)
Authors
Marco Sälzer 
,
Silvia Beddar-Wiesing
-
Part of:
Volume:
30th International Symposium on Temporal Representation and Reasoning (TIME 2023)
Series: Leibniz International Proceedings in Informatics (LIPIcs)
Conference: International Symposium on Temporal Representation and Reasoning (TIME) - License:
Creative Commons Attribution 4.0 International license
- Publication Date: 2023-09-18
File
Document Identifiers
Author Details
- School of Electrical Engineering and Computer Science, University of Kassel, Germany
- marcosaelzer.github.io
Cite As Get BibTex
Marco Sälzer and Silvia Beddar-Wiesing. Time-Aware Robustness of Temporal Graph Neural Networks for Link Prediction (Extended Abstract). In 30th International Symposium on Temporal Representation and Reasoning (TIME 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 278, pp. 19:1-19:3, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)
https://doi.org/10.4230/LIPIcs.TIME.2023.19
Abstract
We present a first notion of a time-aware robustness property for Temporal Graph Neural Networks (TGNN), a recently popular framework for computing functions over continuous- or discrete-time graphs, motivated by recent work on time-aware attacks on TGNN used for link prediction tasks. Furthermore, we discuss promising verification approaches for the presented or similar safety properties and possible next steps in this direction of research.
Subject Classification
ACM Subject Classification
- Computing methodologies → Neural networks
- Security and privacy → Logic and verification
Keywords
- graph neural networks
- temporal
- verification
Metrics
- Access Statistics
-
Total Accesses (updated on a weekly basis)
0PDF Downloads
References
- Artale et al. First-order temporal logic on finite traces: Semantic properties, decidable fragments, and applications. CoRR, abs/2202.00610, 2022. URL: https://arxiv.org/abs/2202.00610.
- Bojchevski et al. Efficient robustness certificates for discrete data: Sparsity-aware randomized smoothing for graphs, images and more. In Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 1003-1013. PMLR, July 2020. URL: https://proceedings.mlr.press/v119/bojchevski20a.html.
- Chen et al. Time-aware gradient attack on dynamic network link prediction. IEEE Trans. Knowl. Data Eng., 35(2):2091-2102, 2023. URL: https://doi.org/10.1109/TKDE.2021.3110580.
- Kazemi et al. Representation learning for dynamic graphs: A survey. J. Mach. Learn. Res., 21:70:1-70:73, 2020. URL: http://jmlr.org/papers/v21/19-447.html.
-
Longa et al. Graph Neural Networks for Temporal Graphs: State of the Art, Open Challenges, and Opportunities. arXiv preprint arXiv:2302.01018, 2023.
-
Skarding et al. Foundations and Modeling of Dynamic Networks using Dynamic Graph Neural Networks: A Survey. IEEE Access, 9:79143-79168, 2021.
- Wu et al. A comprehensive survey on graph neural networks. IEEE Trans. Neural Networks Learn. Syst., 32(1):4-24, 2021. URL: https://doi.org/10.1109/TNNLS.2020.2978386.
- Giuseppe De Giacomo and Moshe Y. Vardi. Linear temporal logic and linear dynamic logic on finite traces. In IJCAI 2013, Proceedings of the 23rd International Joint Conference on Artificial Intelligence, Beijing, China, August 3-9, 2013, pages 854-860. IJCAI/AAAI, 2013. URL: http://www.aaai.org/ocs/index.php/IJCAI/IJCAI13/paper/view/6997.
- Marco Sälzer and Martin Lange. Fundamental limits in formal verification of message-passing neural networks. In The Eleventh International Conference on Learning Representations, 2023. URL: https://openreview.net/forum?id=WlbG820mRH-.
- Daniel Zügner and Stephan Günnemann. Certifiable robustness and robust training for graph convolutional networks. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2019, Anchorage, AK, USA, August 4-8, 2019, pages 246-256. ACM, 2019. URL: https://doi.org/10.1145/3292500.3330905.