DifFaiRec: Generative Fair Recommender with Conditional Diffusion Model
It addresses group unfairness in recommender systems for users, though it appears incremental as it builds on existing diffusion models with fairness modifications.
The paper tackles unfairness in recommender systems, where group disparities in activity lead to recommendation gaps, by proposing DifFaiRec, a generative fair recommender using a conditional diffusion model and a counterfactual module, which outperforms baselines on benchmark datasets.
Although recommenders can ship items to users automatically based on the users' preferences, they often cause unfairness to groups or individuals. For instance, when users can be divided into two groups according to a sensitive social attribute and there is a significant difference in terms of activity between the two groups, the learned recommendation algorithm will result in a recommendation gap between the two groups, which causes group unfairness. In this work, we propose a novel recommendation algorithm named Diffusion-based Fair Recommender (DifFaiRec) to provide fair recommendations. DifFaiRec is built upon the conditional diffusion model and hence has a strong ability to learn the distribution of user preferences from their ratings on items and is able to generate diverse recommendations effectively. To guarantee fairness, we design a counterfactual module to reduce the model sensitivity to protected attributes and provide mathematical explanations. The experiments on benchmark datasets demonstrate the superiority of DifFaiRec over competitive baselines.