FairTL: A Transfer Learning Approach for Bias Mitigation in Deep Generative Models

FairTL: A Transfer Learning Approach for Bias Mitigation in Deep Generative Models

IEEE Journal of Selected Topics in Signal Processing

10.1109/JSTSP.2024.3363419

https://doi.org/10.1109/jstsp.2024.3363419

Christopher T. H. Teo, Milad Abdollahzadeh, Ngai-Man Cheung

generative models, Transfer Learning, fairness, generative adversarial networks (GANs)

14 February 2024

Teo, C. T. H., Abdollahzadeh, M., & Cheung, N.-M. (2024). FairTL: A Transfer Learning Approach for Bias Mitigation in Deep Generative Models. IEEE Journal of Selected Topics in Signal Processing, 18(2), 155–167. https://doi.org/10.1109/jstsp.2024.3363419

This work studies fair generative models. We reveal and quantify the biases in state-of-the-art (SOTA) GANs w.r.t. different sensitive attributes. To address the biases, our main contribution is to propose novel methods to learn fair generative models via transfer learning. Specifically, first, we propose FairTL where we pre-train the generative model with a large biased dataset, then adapt the model using a small fair reference dataset. Second, to further improve sample diversity, we propose FairTL++, containing two additional innovations: 1) aligned feature adaptation, which preserves learned general knowledge while improving fairness by adapting only sensitive attribute-specific parameters, 2) multiple feedback discrimination, which introduces a frozen discriminator for quality feedback and another evolving discriminator for fairness feedback. Taking one step further, we consider an alternative challenging and practical setup. Here, only a pre-trained model is available but the dataset used to pre-train the model is inaccessible. We remark that previous work requires access to large, biased datasets and cannot handle this setup. Extensive experimental results show that FairTL and FairTL++ achieve state-of-the-art performance in quality, diversity and fairness in both setups.

Publisher Copyright

This research / project is supported by the Agency for Science, Technology and Research - Manufacturing, Trade, and Connectivity Programmatic Fund
Grant Reference no. : M23L7b0021

This research / project is supported by the National Research Foundation - AI Singapore Programme
Grant Reference no. : AISG2-TC-2022-007

This research / project is supported by the Changi General Hospital and Singapore University of Technology and Design - HealthTech Innovation Fund
Grant Reference no. : CGH-SUTD-2021-004

© 2024 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/21953

1932-4553
1941-0484

Institute for Infocomm Research