Summary of Learn How to Query From Unlabeled Data Streams in Federated Learning, by Yuchang Sun and Xinran Li and Tao Lin and Jun Zhang
Learn How to Query from Unlabeled Data Streams in Federated Learning
by Yuchang Sun, Xinran Li, Tao Lin, Jun Zhang
First submitted to arxiv on: 11 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC)
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 This research paper presents a novel approach to federated learning (FL), which enables collaborative machine learning among decentralized clients while preserving their local data privacy. The authors address the challenge of selecting informative samples for labeling on clients, given that training data often arrive without ground-truth labels. They propose LeaDQ, a multi-agent reinforcement learning-based solution that learns local policies for distributed clients and guides them towards selecting samples that enhance global model accuracy. Extensive simulations on image and text tasks demonstrate the effectiveness of LeaDQ in advancing FL performance, outperforming benchmark algorithms. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us learn how to make better computer models by working together with other devices while keeping their data private. Usually, training data arrives at these devices without labels, making it hard to decide which samples are most important to label. The authors developed a new way called LeaDQ that uses AI algorithms to help devices choose the right samples to work on. This makes the computer models more accurate and better at learning. |
Keywords
» Artificial intelligence » Federated learning » Machine learning » Reinforcement learning
