Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly

Abstract

Examines federated learning approaches for fine-tuning LLMs on edge devices, analyzing privacy guarantees, communication efficiency, and security trade-offs.

Categories

Framework mappings

@article{woisetschlager2024federated,
  title = {{Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly}},
  author = {Herbert Woisetschläger and Alexander Isenko and Shiqiang Wang and Ruben Mayer and Hans-Arno Jacobsen},
  year = {2024},
  journal = {DEEM@SIGMOD 2024},
  eprint = {2310.03150},
  archivePrefix = {arXiv},
  doi = {10.1145/3650203.3663331},
  url = {https://arxiv.org/abs/2310.03150}
}