Summary of Gradient Coreset For Federated Learning, by Durga Sivasubramanian et al.
Gradient Coreset for Federated Learning
by Durga Sivasubramanian, Lokesh Nagalapatti, Rishabh Iyer, Ganesh Ramakrishnan
First submitted to arxiv on: 13 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 In this paper, researchers address the challenge of developing efficient Federated Learning (FL) models that can learn from data partitioned across multiple clients, including resource-constrained edge devices. To achieve this, they propose novel methods for selecting a representative subset of training data, known as coreset, that balances computational efficiency with compliance to FL’s privacy requirements. These approaches are designed to be robust against noisy data and are extendable to the unique settings of FL. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a way to make machine learning models work better when they’re trained on lots of small pieces of data from different devices. The goal is to make it efficient and private, so that the devices don’t have to do too much work or share their information. The researchers are trying to find a good balance between these things. They want to make sure their method works well even if some of the data is noisy or messy. And they’re doing this all in a way that fits with how machine learning models already work together. |
Keywords
* Artificial intelligence * Federated learning * Machine learning
