Summary of Fedpt: Federated Proxy-tuning Of Large Language Models on Resource-constrained Edge Devices, by Zhidong Gao et al.
FedPT: Federated Proxy-Tuning of Large Language Models on Resource-Constrained Edge Devices
by Zhidong Gao, Yu Zhang, Zhenxiao Zhang, Yanmin Gong, Yuanxiong Guo
First submitted to arxiv on: 1 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 Federated Proxy-Tuning (FedPT), a novel framework for federated fine-tuning of black-box large language models (LLMs). FedPT reduces computation, communication, and memory overhead while maintaining competitive performance compared to directly federated fine-tuning. The approach involves devices collaboratively tuning a smaller LLM and then combining its knowledge with that of the larger pre-trained LLM. This framework offers a promising solution for efficient, privacy-preserving fine-tuning of large LLMs on resource-constrained devices. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning is a way to train AI models without sharing private data. Large language models are very good at doing many tasks, but they need to be adjusted or “fine-tuned” to work well for specific tasks. However, this process requires collecting personal information from people, which raises privacy concerns. To solve this problem, the authors created a new approach called Federated Proxy-Tuning (FedPT). It lets devices work together to adjust a smaller model and then combines that with the knowledge of a larger pre-trained model. This makes it possible to fine-tune large language models without sharing personal data. |
Keywords
» Artificial intelligence » Federated learning » Fine tuning
