2026-07-22T16:01:37Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:19109 2024-03-06T11:03:12Z ddc:004 open_access

Time-Aware Robustness of Temporal Graph Neural Networks for Link Prediction (Extended Abstract) Sälzer, Marco Beddar-Wiesing, Silvia graph neural networks temporal verification 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. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Marco Sälzer and Silvia Beddar-Wiesing 2023 Is Part Of LIPIcs, Volume 278, 30th International Symposium on Temporal Representation and Reasoning (TIME 2023) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.TIME.2023.19 urn:nbn:de:0030-drops-191094 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.TIME.2023.19 eng https://creativecommons.org/licenses/by/4.0/legalcode