Summary of Federated Unlearning For Human Activity Recognition, by Kongyang Chen et al.
Federated Unlearning for Human Activity Recognition
by Kongyang Chen, Dongping zhang, Yaping Chai, Weibin Zhang, Shaowei Wang, Jiaxing Shen
First submitted to arxiv on: 17 Jan 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 learning (FL) method for human activity recognition (HAR) addresses the challenge of user data removal while preserving other clients’ privacy. By selectively removing a portion of training data and fine-tuning using a third-party dataset, the approach achieves comparable unlearning accuracy to retraining methods, with speedups ranging from hundreds to thousands. The method employs KL divergence as a loss function for refining the FL HAR model. A membership inference evaluation method is introduced to assess unlearning effectiveness. |
Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way to remove user data in federated learning while keeping other users’ data private. It’s like a “forgetting” technique that helps keep personal information safe. The method uses a special dataset that’s not related to the model training, and it works really well, even better than some other methods that require more data or computation. |
Keywords
» Artificial intelligence » Activity recognition » Federated learning » Fine tuning » Inference » Loss function