Summary of Bmft: Achieving Fairness Via Bias-based Weight Masking Fine-tuning, by Yuyang Xue et al.
BMFT: Achieving Fairness via Bias-based Weight Masking Fine-tuning
by Yuyang Xue, Junyu Yan, Raman Dutt, Fasih Haider, Jingshuai Liu, Steven McDonagh, Sotirios A. Tsaftaris
First submitted to arxiv on: 13 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Bias-based Weight Masking Fine-Tuning (BMFT) method enhances the fairness of a trained model in fewer epochs without requiring access to original training data. BMFT identifies weights contributing most to biased predictions and applies a two-step debiasing strategy, comprising feature extractor fine-tuning followed by reinitialised classification layer fine-tuning. The method outperforms state-of-the-art techniques on dermatological datasets for diagnostic accuracy and fairness metrics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way to make machine learning models fairer without needing lots of extra data or changing the model entirely. They create a technique called BMFT that looks at which parts of the model are making biased predictions and adjusts those parts to be more fair. This helps keep the model good at predicting things, but now it’s also fair. They tested this on some medical diagnosis datasets and showed that it works better than other methods. |
Keywords
» Artificial intelligence » Classification » Fine tuning » Machine learning
