paper-with-me

홈 › Papers

Fair4Free: Generating High-fidelity Fair Synthetic Samples using Data Free Distillation

2024-10-02 · Md Fahim Sikder, Daniel de Leng, Fredrik Heintz

This work presents Fair4Free, a novel generative model to generate synthetic fair data using data-free distillation in the latent space. Fair4Free can work on the situation when the data is private or inaccessible. In our approach, we first train a teacher model to create fair representation and then distil the knowledge to a student model (using a smaller architecture). The process of distilling the student model is data-free, i.e. the student model does not have access to the training dataset while distilling. After the distillation, we use the distilled model to generate fair synthetic samples. Our extensive experiments show that our synthetic samples outperform state-of-the-art models in all three criteria (fairness, utility and synthetic quality) with a performance increase of 5% for fairness, 8% for utility and 12% in synthetic quality for both tabular and image datasets.

📄 PDF Abstract BibTeX arXiv:2410.01423

Code (0)

등록된 구현이 없습니다.

Tasks

Fairness

Similar Papers 제목 키워드 기반

Generating Synthetic Fair Syntax-agnostic Data by Learning and Distilling Fair Representation

2024-08-20 · Md Fahim Sikder, Resmi Ramachandranpillai, Daniel de Leng, Fredrik Heintz

Data Fairness is a crucial topic due to the recent wide usage of AI powered applications. Most of the real-world data is filled with human or machine biases and when those data are being used to train AI models, there is…

FairnessKnowledge Distillation

Characterizing the risk of fairwashing

2021-06-14 · NeurIPS 2021 12 · Ulrich Aïvodji, Hiromi Arai, Sébastien Gambs, Satoshi Hara

Fairwashing refers to the risk that an unfair black-box model can be explained by a fairer model through post-hoc explanation manipulation. In this paper, we investigate the capability of fairwashing attacks by analyzing…

Fairness

DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks

2021-10-25 · NeurIPS 2021 12 · Boris van Breugel, Trent Kyono, Jeroen Berrevoets, Mihaela van der Schaar

Machine learning models have been criticized for reflecting unfair biases in the training data. Instead of solving for this by introducing fair learning algorithms directly, we focus on generating fair synthetic data, su…

Fairness

FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models

2025-10-24 · Zihao Fu, Ryan Brown, Shun Shao, Kai Rawal 외 arxiv

Text-to-image diffusion models, such as Stable Diffusion, have demonstrated remarkable capabilities in generating high-quality and diverse images from natural language prompts. However, recent studies reveal that these m…

Text-to-Image Generation

FAME: Fairness-aware Attention-modulated Video Editing

2025-10-27 · Zhangkai Wu, Xuhui Fan, Zhongyuan Xie, Kaize Shi 외 arxiv

Training-free video editing (VE) models tend to fall back on gender stereotypes when rendering profession-related prompts. We propose \textbf{FAME} for \textit{Fairness-aware Attention-modulated Video Editing} that mitig…