Summary of Efficiently Assemble Normalization Layers and Regularization For Federated Domain Generalization, by Khiem Le et al.
Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalization
by Khiem Le, Long Ho, Cuong Do, Danh Le-Phuoc, Kok-Seng Wong
First submitted to arxiv on: 22 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
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 paper proposes a novel Federated Domain Generalization (FedDG) method called gPerXAN to address the issue of domain shift in machine learning. FedDG aims to train a global model using collaborative clients while preserving privacy and generalizing well to unseen domains. The proposed method relies on a normalization scheme with a guiding regularizer, allowing client models to selectively filter domain-specific features and capture domain-invariant representations. Experimental results on benchmark datasets and a real-world medical dataset show that gPerXAN outperforms existing methods in addressing the problem of domain shift. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper tries to solve a big problem in machine learning called domain shift. Domain shift is when a model doesn’t work well when it’s tested with new data that’s different from what it was trained on. The authors want to make sure their model works well even if it sees new data. They came up with a new way to do this, called gPerXAN, which helps the model focus on important features and ignore features that are specific to one type of data. They tested their method on several datasets and found that it did better than other methods at solving this problem. |
Keywords
* Artificial intelligence * Domain generalization * Machine learning
