Personalized Collaborative Fine-Tuning for On-Device Large Language Models
Research Area: Compute efficient LMs, LMs for everyone, LMs and the world
Keywords: Collaborative fine-tuning, On-device LLMs, Personalized learning
TL;DR: We explore on-device collaborative fine-tuning of large language models under heterogeneous and scarce local datasets.
Abstract: We explore on-device collaborative fine-tuning of large language models under limited local data availability. We introduce three distinct dynamic collaborator selection schemes, allowing trust-weighted personalized update aggregation: model-similarity-based, prediction-similarity-based and validation-performance-based. To minimize communication overhead, we integrate Low-Rank Adaptation (LoRA) and only exchange LoRA model updates. Our protocols, driven by prediction and performance metrics, surpass both FedAvg and local fine-tuning methods, which is particularly evident in realistic distributed scenarios with more diverse local data distributions. The results underscore the effectiveness of our approach in addressing heterogeneity and scarcity of the local datasets.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html
Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html
Submission Number: 837
Loading