DifFaiRec: Generative Fair Recommender with Conditional Diffusion Model

TL;DR

A novel recommendation algorithm named Diffusion-based Fair Recommender (DifFaiRec) is proposed to provide fair recommendations and a counterfactual module is designed to reduce the model sensitivity to protected attributes and provide mathematical explanations.

Abstract

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.

Figures (3)

• Figure 1: The flowchart of DifFaiRec. The original rating vector is $\mathbf{x}_0$. In the forward process, the vector is added with Gaussian noise $T$ times, becoming $\mathbf{x}_T$. In the reverse process, $\mathbf{x}_T$, the group vectors, and the time step are fed into DifFaiRec to estimate the noise, and then the missing ratings in $\mathbf{x}_0$ can be recovered after $T$ times of denoising.
• Figure 2: Ablation study. The blue bar draws the performance of the proposed model and the orange bar draws the performance of the model without using the condition encoder $\mathrm{Enc}$ (i.e. $\mathrm{MLP}_2$). Additionally, the black dotted line illustrates the performance of the model without the counterfactual module.
• Figure 3: Results of impact of hyper-parameters. The blue line represents the variation of recall and the orange line represents the variation of ndcg.