Fair Image Generation from Pre-trained Models by Probabilistic Modeling

Mahdi Ahmadi, John Leland, Agneet Chatterjee, YooJung Choi

Keywords: Image Generation, Fairness, Probabilistic Modeling

Abstract: The production of high-fidelity images by generative models has been transformative to the space of artificial intelligence. Yet, while the generated images are of high quality, the images tend to mirror biases present in the dataset they are trained on. While there has been an influx of work to tackle this issue, existing works typically rely on fine-tuning an existing generative model which requires costly retraining time. In this paper, we use a family of tractable probabilistic models called probabilistic circuits (PCs), which can be equipped to a pre-trained generative model to produce fair images without fine-tuning. We show that for a given trained generative model, our method only requires a small fair reference dataset to train the PC, removing the need to retrain the generative model on a large dataset. Our experimental results show that the proposed method achieves a balance between training resources and ensuring fairness and quality of generated images.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 11808