{"type":"ScholarlyArticle","title":"Towards Comprehensive and Prerequisite-Free Explainer for Graph Neural Networks","authors":[{"name":"Han Zhang","slug":"han-zhang","given":"Han","family":"Zhang","affiliation":""},{"name":"Yan Wang","slug":"yan-wang","given":"Yan","family":"Wang","affiliation":""},{"name":"Guanfeng Liu","slug":"guanfeng-liu","given":"Guanfeng","family":"Liu","affiliation":""},{"name":"Pengfei Ding","slug":"pengfei-ding","given":"Pengfei","family":"Ding","affiliation":""},{"name":"Huaxiong Wang","slug":"huaxiong-wang","given":"Huaxiong","family":"Wang","affiliation":""},{"name":"Kwok-Yan Lam","slug":"kwok-yan-lam","given":"Kwok-Yan","family":"Lam","affiliation":""}],"abstract":"To enhance the reliability and credibility of graph neural networks (GNNs) and improve the transparency of their decision logic, a new field of explainability of GNNs (XGNN) has emerged. However, two major limitations severely degrade the performance and hinder the generalizability of existing XGNN methods: they (a) fail to capture the complete decision logic of GNNs across diverse distributions in the entire dataset's sample space, and (b) impose strict prerequisites on edge properties and GNN internal accessibility. To address these limitations, we propose OPEN, a novel cOmprehensive and Prerequisite-free Explainer for GNNs. OPEN, as the first work in the literature, can infer and partition the entire dataset's sample space into multiple environments, each containing graphs that follow a distinct distribution. OPEN further learns the decision logic of GNNs across different distributions by sampling subgraphs from each environment and analyzing their predictions, thus eliminating the need for strict prerequisites. Experimental results demonstrate that OPEN captures nearly complete decision logic of GNNs, outperforms state-of-the-art methods in fidelity while maintaining similar efficiency, and enhances robustness in real-world scenarios.","doi":"10.24963/ijcai.2025/1051","url":"https://ijcai.org/proceedings/2025/1051","pdf":"https://ijcai.org/proceedings/2025/1051.pdf","markdown":"https://ijcai.org/proceedings/2025/1051.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/1051","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":"AI4Tech: AI Enabling Technologies","track":"AI4Tech: AI Enabling Technologies","number":1051,"pages":{"first":9456,"last":9464},"keywords":["Advanced AI4Tech: AI4Tech foundations","Domain-specific AI4Tech: AI4Safety","Emerging AI4Tech: Ethical and responsible AI4Tech"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}