Summary of C2a: Client-customized Adaptation For Parameter-efficient Federated Learning, by Yeachan Kim et al.
C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning
by Yeachan Kim, Junho Kim, Wing-Lam Mok, Jun-Hyung Park, SangKeun Lee
First submitted to arxiv on: 1 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
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 paper explores the limitations of pre-trained language models (PLMs) in federated learning (FL), where large memory footprints hinder efficient training. The authors propose Client-Customized Adaptation (C2A), a hypernetwork-based framework that generates client-specific adapters to address heterogeneity among clients, improving convergence speed and efficiency. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In simple terms, this paper solves a problem with using big language models in sharing data between devices. It proposes a new way to make the model work better by creating special adapters for each device. The authors tested their idea and found it worked better than other methods in scenarios where devices have different types of data or labels. |
Keywords
» Artificial intelligence » Federated learning
