Summary of Fed-zoe: Communication-efficient Over-the-air Federated Learning Via Zeroth-order Estimation, by Jonggyu Jang et al.
Fed-ZOE: Communication-Efficient Over-the-Air Federated Learning via Zeroth-Order Estimation
by Jonggyu Jang, Hyeonsu Lyu, David J. Love, Hyun Jong Yang
First submitted to arxiv on: 21 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Signal Processing (eess.SP)
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 Zeroth-Order Estimation (Fed-ZOE) framework is an efficient solution for securely and efficiently leveraging decentralized edge data in 6G and beyond networks. By compressing local model update vectors before transmission, Fed-ZOE preserves the superposition property of over-the-air federated learning (OtA-FL) while reducing communication costs. This approach achieves comparable performance to OtA-FL on ResNet-18 with datasets such as CIFAR-10, TinyImageNet, SVHN, CIFAR-100, and Brain-CT. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Fed-ZOE is a new way to train AI models using data from many devices connected over the internet. This helps keep our personal data private while still allowing us to get better results. It’s like compressing a big file so it takes less time to send. The technique works well on lots of different kinds of data and can be used for things like recognizing images or understanding speech. |
Keywords
» Artificial intelligence » Federated learning » Resnet
