Metraipolis › archive › dc_4bb19f42ed07
Reachability-Based Formal Verification of Graph Neural Networks with Node and Edge Features — arXiv:2609.30079
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30079
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:28:00.797Z
- SHA-256 of the archived text
3b02e1a3edf3ef609c31a88585aa234562df7fce3e68713796008c854d5c13e6- Stable URL of this page
https://metraipolis.com/documento/dc_4bb19f42ed07
How to cite
Reachability-Based Formal Verification of Graph Neural Networks with Node and Edge Features — arXiv:2609.30079 — arXiv (en), https://arxiv.org/abs/2609.30079 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4bb19f42ed07 (Metraipolis archive dc_4bb19f42ed07, sha256 3b02e1a3edf3ef609c31a88585aa234562df7fce3e68713796008c854d5c13e6)
BibTeX
@misc{dc4bb19f42ed07,
title = {Reachability-Based Formal Verification of Graph Neural Networks with Node and Edge Features — arXiv:2609.30079},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30079},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4bb19f42ed07; sha256 3b02e1a3edf3ef609c31a88585aa234562df7fce3e68713796008c854d5c13e6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30079. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Graph neural networks (GNNs) have become a prominent approach for developing fast, topology-aware surrogates in electric power systems, supporting tasks such as power flow (PF) analysis, optimal power flow (OPF) estimation, and cascading failure analysis (CFA). Despite this growing use, formally verifying GNN-based models remains challenging, with existing methods limited in scope. We extend the neural network verification (NNV) framework to graph-structured inputs through GraphStar sets, a generalization of Star sets that captures uncertainty over both node and edge features. This extension enables the propagation of linear message-passing operations and the sound approximation of ReLU nonlinearities for GNN architectures, including graph convolutional network (GCN) and graph isomorphism network with edge features (GINE) layers. We evaluate GNNV across three power system tasks, PF, OPF, and CFA, on the IEEE-24, IEEE-39, and IEEE-118 test cases, as well as two standard graph classification benchmarks, ENZYMES and PROTEINS. Our results show that GNNV provides tighter robustness guarantees than CORA on graph classification models with ReLU-based activations and, for the first time, delivers edge-aware robustness guarantees for GINE-based PF and OPF models under joint node and edge perturbations. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.30079 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T03:50:58.233Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).