Summary of Estimating Before Debiasing: a Bayesian Approach to Detaching Prior Bias in Federated Semi-supervised Learning, by Guogang Zhu et al.
Estimating before Debiasing: A Bayesian Approach to Detaching Prior Bias in Federated Semi-Supervised Learning
by Guogang Zhu, Xuefeng Liu, Xinghao Wu, Shaojie Tang, Chao Tang, Jianwei Niu, Hao Su
First submitted to arxiv on: 30 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Distributed, Parallel, and Cluster Computing (cs.DC)
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 Federated Semi-Supervised Learning (FSSL) tackles the issue of prediction bias in models trained on heterogeneous data. By exploring label prior bias within training data, researchers develop a debiasing method called FedDB. This approach utilizes Average Prediction Probability of Unlabeled Data (APP-U) to refine pseudo-labeling and formulate unbiased aggregate weights during model aggregation. Experimental results show that FedDB outperforms existing FSSL methods. The paper proposes a Bayesian perspective on prediction bias and introduces FedDB, which can be employed for collaborative training of models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated Semi-Supervised Learning helps machines learn from different data sources without becoming biased. Researchers found that the problem comes from how we label this data. They created a new method called FedDB to fix this issue. It uses a special calculation to make sure the model is fair and unbiased. This new approach works better than previous methods. |
Keywords
» Artificial intelligence » Probability » Semi supervised
