Fairness for All: Investigating Harms to Within-Group Individuals in Producer Fairness Re-ranking Optimization -- A Reproducibility Study

TL;DR

This study reproduces and critiques producer fairness re-ranking methods in recommender systems, revealing harms to colder items within groups, and proposes an amendment that balances fairness and accuracy while enhancing recommendation diversity.

Contribution

It identifies the unintended harm to colder items caused by existing fairness re-ranking approaches and introduces a new regulation method to improve within-group fairness without sacrificing accuracy.

Findings

Significant harm to colder items in existing PFR approaches.

Improved subgroup fairness (SGF) from 0.3104 to 0.9442.

Enhanced group fairness with minimal impact on accuracy.

Abstract

Recommender systems are widely used to provide personalized recommendations to users. Recent research has shown that recommender systems may be subject to different types of biases, such as popularity bias, leading to an uneven distribution of recommendation exposure among producer groups. To mitigate this, producer-centered fairness re-ranking (PFR) approaches have been proposed to ensure equitable recommendation utility across groups. However, these approaches overlook the harm they may cause to within-group individuals associated with colder items, which are items with few or no interactions. This study reproduces previous PFR approaches and shows that they significantly harm colder items, leading to a fairness gap for these items in both advantaged and disadvantaged groups. Surprisingly, the unfair base recommendation models were providing greater exposure opportunities to these individual cold items, even though at the group level, they appeared to be unfair. To address this issue, the study proposes an amendment to the PFR approach that regulates the number of colder items recommended by the system. This modification achieves a balance between accuracy and producer fairness while optimizing the selection of colder items within each group, thereby preventing or reducing harm to within-group individuals and augmenting the novelty of all recommended items. The proposed method is able to register an increase in sub-group fairness (SGF) from 0.3104 to 0.3782, 0.6156, and 0.9442 while also improving group-level fairness (GF) (112% and 37% with respect to base models and traditional PFR). Moreover, the proposed method achieves these improvements with minimal or no reduction in accuracy (or even an increase sometimes). We evaluate the proposed method on various recommendation datasets and demonstrate promising results independent of the underlying model or datasets.