Summary of Federated Learning with Only Positive Labels by Exploring Label Correlations, By Xuming An et al.
Federated Learning with Only Positive Labels by Exploring Label Correlations
by Xuming An, Dui Wang, Li Shen, Yong Luo, Han Hu, Bo Du, Yonggang Wen, Dacheng Tao
First submitted to arxiv on: 24 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR)
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 Federated Averaging by exploring Label Correlations (FedALC) method addresses issues in multi-label classification under federated learning settings, where trivial or poor performance may be obtained due to lack of label correlations. FedALC estimates label correlations and utilizes them to improve model training, outperforming existing methods on popular datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning is a way for multiple users to work together on a project without sharing their individual data. This paper focuses on a specific problem called multi-label classification, where we want to predict multiple labels or categories from some input data. The authors discovered that current approaches can have poor performance if the data doesn’t contain examples of all the labels being predicted at once. To fix this, they created a new method called FedALC, which looks at how different labels are related and uses that information to improve the model’s accuracy. |
Keywords
» Artificial intelligence » Classification » Federated learning
