Counterfactual Explanation for Fairness in Recommendation

TL;DR

This paper introduces CFairER, a novel method using counterfactual explanations and reinforcement learning to identify minimal attribute changes that improve fairness in recommendation systems, especially for discrete attributes.

Contribution

It proposes a new counterfactual explanation framework for recommendation fairness that avoids greedy search and handles discrete attributes using HINs and reinforcement learning.

Findings

CFairER generates faithful explanations for fairness.

The method maintains strong recommendation performance.

Attentive action pruning reduces computational complexity.

Abstract

Fairness-aware recommendation eliminates discrimination issues to build trustworthy recommendation systems.Explaining the causes of unfair recommendations is critical, as it promotes fairness diagnostics, and thus secures users' trust in recommendation models. Existing fairness explanation methods suffer high computation burdens due to the large-scale search space and the greedy nature of the explanation search process. Besides, they perform score-based optimizations with continuous values, which are not applicable to discrete attributes such as gender and race. In this work, we adopt the novel paradigm of counterfactual explanation from causal inference to explore how minimal alterations in explanations change model fairness, to abandon the greedy search for explanations. We use real-world attributes from Heterogeneous Information Networks (HINs) to empower counterfactual reasoning on discrete attributes. We propose a novel Counterfactual Explanation for Fairness (CFairER) that generates attribute-level counterfactual explanations from HINs for recommendation fairness. Our CFairER conducts off-policy reinforcement learning to seek high-quality counterfactual explanations, with an attentive action pruning reducing the search space of candidate counterfactuals. The counterfactual explanations help to provide rational and proximate explanations for model fairness, while the attentive action pruning narrows the search space of attributes. Extensive experiments demonstrate our proposed model can generate faithful explanations while maintaining favorable recommendation performance.