Summary of Global and Local Prompts Cooperation Via Optimal Transport For Federated Learning, by Hongxia Li et al.
Global and Local Prompts Cooperation via Optimal Transport for Federated Learning
by Hongxia Li, Wei Huang, Jingya Wang, Ye Shi
First submitted to arxiv on: 29 Feb 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 The paper presents a new approach to prompt learning in visual-language models, called Federated Prompts Cooperation via Optimal Transport (FedOTP). This method aims to reduce communication costs and promote local training on insufficient data by integrating powerful pretrained models into federated learning frameworks. The authors address the challenge of severe data heterogeneities, including both label and feature shifts, by introducing efficient collaborative prompt learning strategies that capture diverse category traits per client. They learn a global prompt to extract consensus knowledge among clients and a local prompt to capture client-specific category characteristics. Optimal Transport is employed to align local visual features with these prompts, balancing global consensus and local personalization. The paper shows that FedOTP outperforms state-of-the-art methods on datasets with various types of heterogeneities. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about a new way to make computer models better at understanding images. It’s called Federated Prompts Cooperation via Optimal Transport, or FedOTP for short. The goal is to help these models work better even when they don’t have much data to learn from. To do this, the authors come up with a special approach that helps different parts of an image focus on what’s important. They test their method on many different types of images and show that it works better than other methods. |
Keywords
* Artificial intelligence * Federated learning * Prompt
