Adaptive Autoguidance for Item-Side Fairness in Diffusion Recommender Systems

TL;DR

A2G-DiffRec is introduced, a diffusion recommender that incorporates adaptive autoguidance, where the main model is guided by a less-trained version of itself, where the main model is guided by a less-trained version of itself.

Abstract

Diffusion recommender systems achieve strong recommendation accuracy but often suffer from popularity bias, resulting in unequal item exposure. To address this shortcoming, we introduce A2G-DiffRec, a diffusion recommender that incorporates adaptive autoguidance, where the main model is guided by a less-trained version of itself. Instead of using a fixed guidance weight, A2G-DiffRec learns to adaptively weigh the outputs of the main and weak models during training, supervised by a popularity regularization that promotes balanced exposure across items with different popularity levels. Experimental results on the MovieLens-1M, Foursquare-Tokyo, and Music4All-Onion datasets show that A2G-DiffRec is effective in enhancing item-side fairness at a marginal cost of accuracy reduction compared to existing guided diffusion recommenders and other non-diffusion baselines.

Figures (1)

• Figure 1: Overview of A2G-DiffRec. During training, AAN learns to produce a weight to fuse the output of the main and the weak model at each step; the same fusion is applied during sampling.