{"type":"ScholarlyArticle","title":"Verifying Quantized Graph Neural Networks is PSPACE-complete","authors":[{"name":"Marco Sälzer","slug":"marco-salzer","given":"Marco","family":"Sälzer","affiliation":""},{"name":"Francois Schwarzentruber","slug":"francois-schwarzentruber","given":"François","family":"Schwarzentruber","affiliation":""},{"name":"Nicolas Troquard","slug":"nicolas-troquard","given":"Nicolas","family":"Troquard","affiliation":""}],"abstract":"In this paper, we investigate verification of quantized Graph Neural Networks (GNNs), where some fixed-width arithmetic is used to represent numbers.\r\nWe introduce the linear-constrained validity (LVP) problem for verifying GNNs properties, and provide an efficient translation from LVP instances into a logical language. We show that LVP is in PSPACE, for any reasonable activation functions. We provide a proof system. We also prove PSPACE-hardness, indicating that while reasoning about quantized GNNs is feasible, it remains generally computationally challenging.","doi":"10.24963/ijcai.2025/519","url":"https://ijcai.org/proceedings/2025/519","pdf":"https://ijcai.org/proceedings/2025/0519.pdf","markdown":"https://ijcai.org/proceedings/2025/519.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/519","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Knowledge Representation and Reasoning","track":"Main Track","number":519,"pages":{"first":4660,"last":4668},"keywords":["Knowledge Representation and Reasoning: KRR: Computational complexity of reasoning","Machine Learning: ML: Other","Knowledge Representation and Reasoning: KRR: Automated reasoning and theorem proving"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}