{"type":"ScholarlyArticle","title":"FairCognizer: A Model for Accurate Predictions with Inherent Fairness Evaluation (Extended Abstract)","authors":[{"name":"Adda Akram Bendoukha","slug":"adda-akram-bendoukha","given":"Adda Akram","family":"Bendoukha","affiliation":""},{"name":"Nesrine Kaaniche","slug":"nesrine-kaaniche","given":"Nesrine","family":"Kaaniche","affiliation":""},{"name":"Aymen Boudguiga","slug":"aymen-boudguiga","given":"Aymen","family":"Boudguiga","affiliation":""},{"name":"Renaud Sirdey","slug":"renaud-sirdey","given":"Renaud","family":"Sirdey","affiliation":""}],"abstract":"Algorithmic fairness is a critical challenge in building trustworthy Machine Learning (ML)  models. ML classifiers strive to make predictions that closely match real-world observations (ground truth). However, if the ground truth data itself reflects biases against certain sub-populations, a dilemma arises: prioritize fairness and potentially reduce accuracy, or emphasize accuracy at the expense of fairness.\r\nThis work proposes a novel training framework that goes beyond achieving high accuracy. Our framework trains a classifier to not only deliver optimal predictions but also to identify potential fairness risks associated with each prediction. \r\nTo do so, we specify a dual-labeling strategy where the second label contains a per-prediction fairness evaluation, referred to as an unfairness risk evaluation. In addition, we identify a subset of samples as highly vulnerable to group-unfair classifiers.\r\nOur experiments demonstrate that our classifiers attain optimal accuracy levels on both the Adult-Census-Income and Compas-Recidivism datasets. Moreover, they identify unfair predictions with nearly 75% accuracy at the cost of expanding the size of the classifier by 45%.","doi":"10.24963/ijcai.2025/1207","url":"https://ijcai.org/proceedings/2025/1207","pdf":"https://ijcai.org/proceedings/2025/1207.pdf","markdown":"https://ijcai.org/proceedings/2025/1207.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/1207","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":"Sister Conferences Best Papers","track":"Sister Conferences Best Papers","number":1207,"pages":{"first":10869,"last":10874},"keywords":["Sister Conferences Best Papers: AI Ethics, Trust, Fairness"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}