Fair Learning for Bias Mitigation and Quality Optimization in Paper Recommendation

ArXi:2603.11936v1 Announce Type: new Despite frequent double-blind review, graphic biases of authors still disadvantage the underrepresented groups. We present Fair-PaperRec, a MultiLayer Perceptron (MLP)-based model that addresses graphic disparities in post-review paper acceptance decisions while maintaining high-quality requirements. Our methodology penalizes graphic disparities while preserving quality through intersectional criteria (e.g., race, country) and a customized fairness loss, in contrast to heuristic approaches.