Self-Paced Fair Ranking with Loss as a Proxy for Bias

Hai Son Le, Shirin Seyedsalehi, Morteza Zihayat, Ebrahim Bagheri
January 2026

Abstract

This paper presents a self-paced learning approach for fair ranking, using loss as a proxy for bias to improve fairness in information retrieval systems while maintaining ranking quality.

Type
Conference paper
Publication
Proceedings of the ACM International Conference on Web Search and Data Mining

This work introduces a self-paced learning framework for fair ranking that uses loss functions as proxies for bias measurement.

Fair Ranking Bias Mitigation Self-Paced Learning Information Retrieval Fairness
Hai Son Le
Hai Son Le
Master’s Student

Hai Son Le is a Master’s student in the Human-Centered Machine Intelligence Lab, working on research projects in machine learning and data science.

Shirin Seyedsalehi
PhD Student (Alumni)

Shirin Seyedsalehi is a former PhD student and alumna of the Human-Centered Machine Intelligence Lab.

Morteza Zihayat
Morteza Zihayat
Principal Investigator

Dr. Morteza Zihayat is a Canada Research Chair (CRC) in Human-Centered AI and Associate Professor at Toronto Metropolitan University, Faculty of Engineering and Architectural Science. He also holds appointments as Adjunct Associate Professor at the University of Waterloo (Management Sciences) and IBM Faculty Fellow at IBM Centre for Advanced Studies. He is the Director of the Human-Centered Machine Intelligence Lab.