Summary of Federated Learning For Discrete Optimal Transport with Large Population Under Incomplete Information, by Navpreet Kaur et al.
Federated Learning for Discrete Optimal Transport with Large Population under Incomplete Information
by Navpreet Kaur, Juntao Chen, Yingdong Lu
First submitted to arxiv on: 12 Nov 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- 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 The paper introduces a discrete optimal transport framework for efficiently allocating resources between sources and targets, particularly in scenarios involving large and heterogeneous populations. The proposed model is designed to handle type distributions of target populations, which can be known or unknown. For known distributions, the authors propose a fully distributed algorithm, while for unknown distributions, they develop a federated learning-based approach that preserves privacy. Case studies are presented to evaluate the performance of the learning algorithm. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about using a new way to allocate resources between people and things, which works really well even when there are many different types of people involved. The researchers came up with two ways to do this: one where they know what kinds of people they’re working with, and another where they don’t. They tested their ideas on real-world problems and showed that they can be very effective. |
Keywords
» Artificial intelligence » Federated learning
