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 fairness-aware regularization that promotes balanced exposure across items with different popularity levels. Experimental results on three public 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.
Citation
Zihan Li, Gustavo Escobedo, Marta Moscati, Oleg Lesota, Markus Schedl
Adaptive Autoguidance for Item-Side Fairness in Diffusion Recommender Systems
Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2026.
BibTeX
@inproceedings{Li2026ada_auto,
title = {Adaptive Autoguidance for Item-Side Fairness in Diffusion Recommender Systems},
author = {Li, Zihan and Escobedo, Gustavo and Moscati, Marta and Lesota, Oleg and Schedl, Markus},
booktitle = {Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval},
url = {https://arxiv.org/abs/2602.14706},
year = {2026}
}