Tootfinder

Flexible Fairness Learning via Inverse Conditional Permutation
Yuheng Lai, Leying Guan
https://arxiv.org/abs/2404.05678 https://arxiv…

Flexible Fairness Learning via Inverse Conditional Permutation
Equalized odds, as a popular notion of algorithmic fairness, aims to ensure that sensitive variables, such as race and gender, do not unfairly influence the algorithm prediction when conditioning on the true outcome. Despite rapid advancements, most of the current research focuses on the violation of equalized odds caused by one sensitive attribute, leaving the challenge of simultaneously accounting for multiple attributes under-addressed. We address this gap by introducing a fairness learning …

Post-Training Attribute Unlearning in Recommender Systems
Chaochao Chen, Yizhao Zhang, Yuyuan Li, Dan Meng, Jun Wang, Xiaoli Zheng, Jianwei Yin
https://arxiv.org/abs/2403.06737

Post-Training Attribute Unlearning in Recommender Systems
With the growing privacy concerns in recommender systems, recommendation unlearning is getting increasing attention. Existing studies predominantly use training data, i.e., model inputs, as unlearning target. However, attackers can extract private information from the model even if it has not been explicitly encountered during training. We name this unseen information as \textit{attribute} and treat it as unlearning target. To protect the sensitive attribute of users, Attribute Unlearning (AU) …

This https://arxiv.org/abs/2404.07494 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Adaptive Fair Representation Learning for Personalized Fairness in Recommendations via Information Alignment
Personalized fairness in recommendations has been attracting increasing attention from researchers. The existing works often treat a fairness requirement, represented as a collection of sensitive attributes, as a hyper-parameter, and pursue extreme fairness by completely removing information of sensitive attributes from the learned fair embedding, which suffer from two challenges: huge training cost incurred by the explosion of attribute combinations, and the suboptimal trade-off between fairne…

Adaptive Fair Representation Learning for Personalized Fairness in Recommendations via Information Alignment
XInyu Zhu, Lilin Zhang, Ning Yang
https://arxiv.org/abs/2404.07494

Adaptive Fair Representation Learning for Personalized Fairness in Recommendations via Information Alignment
Personalized fairness in recommendations has been attracting increasing attention from researchers. The existing works often treat a fairness requirement, represented as a collection of sensitive attributes, as a hyper-parameter, and pursue extreme fairness by completely removing information of sensitive attributes from the learned fair embedding, which suffer from two challenges: huge training cost incurred by the explosion of attribute combinations, and the suboptimal trade-off between fairne…