Integration of large language models and federated learning
Chaochao Chen, Xiaohua Feng, Yuyuan Li, Lingjuan Lyu, Jun Zhou, Xiaolin Zheng, Jianwei Yin · 2024
Read Integration of large language models and federated learning by Chaochao Chen, Xiaohua Feng, Yuyuan Li, Lingjuan Lyu, Jun Zhou, Xiaolin Zheng, Jianwei Yin (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11701858.txt.
Description
Chaochao Chen and co-authors review the two-way marriage of large language models and federated learning, in this 2024 paper. Big models hunger for quality data that privacy rules lock away; federated learning trains across owners without moving the data. Each side can also fix the other's weakness: models bring task skill to scattered training, while federation brings fresh data to models. The authors sort the fusion into three layers.
They cover part-level swaps, like using model tricks inside federated systems, through full mergers of the two frameworks. Healthcare, finance, and education get worked examples. Open problems include cost, uneven data, and attack surfaces. The review closes with directions the authors see as most promising for this fast-growing crossroads.
Catalog record
| CREATOR | Chaochao Chen, Xiaohua Feng, Yuyuan Li, Lingjuan Lyu, Jun Zhou, Xiaolin Zheng, Jianwei Yin |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 95 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |