Imperceptible Fairness in Top-k Ranking Algorithms

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


MPhil Thesis Defence


Title: "Imperceptible Fairness in Top-k Ranking Algorithms"

By

Mr. Junjie LIU


Abstract:

The top-k ranking of people and items in algorithmic systems helps people
extract information and make decisions from vast amounts of data, raising
widespread concerns about the fairness of these systems. Recent studies
have considered various fairness issues in these systems, including
fairness with different definitions and fairness for different user groups.
In this paper, we show that users can notice violations in these rankings,
leading users to distrust these rankings and thereby preventing the
achievement of fairness goals. In particular, most known mechanisms try to
minimize the utility loss incurred to achieve fairness, and these attempts
provide loopholes for users to detect ranking violations (called fairness
failures). We introduce a model called imperceptible fairness, which deals
with fairness failure and proposes a feasible solution. Our experiments
show that fairness failures are a practical concern for real datasets and
that our algorithm can prevent these fairness failures with little overhead.
Compared to baseline algorithms, we reduce the probability of adjacent pair
fairness failure by over 16.66% or the probability of additional
information fairness failure by over 4.39% in most scenarios.


Date:                   Friday, 9 January 2026

Time:                   2:00pm - 4:00pm

Venue:                  Room 3494
                        Lifts 25/26

Chairman:               Prof. Ke YI

Committee Members:      Prof. Raymond WONG (Supervisor)
                        Dr. Wilfred NG