{"type":"ScholarlyArticle","title":"Towards Fair Graph Learning Without Demographic Supervision","authors":[{"name":"Zichong Wang","slug":"zichong-wang","given":"Zichong","family":"Wang","affiliation":""},{"name":"Zhipeng Yin","slug":"zhipeng-yin","given":"Zhipeng","family":"Yin","affiliation":""},{"name":"Mo Sha","slug":"mo-sha","given":"Mo","family":"Sha","affiliation":""},{"name":"Xiaofeng Gao","slug":"xiaofeng-gao","given":"Xiaofeng","family":"Gao","affiliation":""},{"name":"Xiaoli Li","slug":"xiaoli-li","given":"Xiaoli","family":"Li","affiliation":""},{"name":"Wenbin Zhang","slug":"wenbin-zhang","given":"Wenbin","family":"Zhang","affiliation":""}],"abstract":"Graph Neural Networks (GNNs) have demonstrated strong predictive performance across a wide range of applications. However, their increasing deployment has raised critical fairness concerns, as these models can inherit and amplify existing biases. Most existing fairness approaches rely on explicit demographic information, either directly available or inferred, to measure and mitigate bias. In real-world settings, however, such information is often unavailable or legally prohibited to infer due to privacy concerns, legal restrictions, or regulatory constraints, which substantially limits the applicability of these methods. To address this challenge, we propose Demographic-Independent Fair Graph Learning (DIFGL), a novel framework for fair graph learning without demographic supervision. DIFGL mitigates group unfairness by minimizing disparities in individual treatment across implicitly identified subgroups, thereby enforcing fairness without requiring explicit demographic information. Extensive experiments on benchmark datasets demonstrate that DIFGL achieves significant improvements in fairness while maintaining competitive predictive performance.","doi":"10.24963/ijcai.2026/89","url":"https://ijcai.org/proceedings/2026/89","pdf":"https://ijcai.org/proceedings/2026/0089.pdf","markdown":"https://ijcai.org/proceedings/2026/89.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/89","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI Ethics, Trust, Fairnes","track":"Main Track","number":89,"pages":{"first":789,"last":797},"keywords":["AI Ethics, Trust, Fairnes: Fairness and diversity","AI Ethics, Trust, Fairnes: AI and law, governance, regulation","AI Ethics, Trust, Fairnes: Ethical, legal and societal issues"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}