Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cho, Yae Jee, Liu, Luyang, Xu, Zheng, Fahrezi, Aldi, Joshi, Gauri
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917594748944384
author Cho, Yae Jee
Liu, Luyang
Xu, Zheng
Fahrezi, Aldi
Joshi, Gauri
author_facet Cho, Yae Jee
Liu, Luyang
Xu, Zheng
Fahrezi, Aldi
Joshi, Gauri
contents Foundation models (FMs) adapt well to specific domains or tasks with fine-tuning, and federated learning (FL) enables the potential for privacy-preserving fine-tuning of the FMs with on-device local data. For federated fine-tuning of FMs, we consider the FMs with small to medium parameter sizes of single digit billion at maximum, referred to as on-device FMs (ODFMs) that can be deployed on devices for inference but can only be fine-tuned with parameter efficient methods. In our work, we tackle the data and system heterogeneity problem of federated fine-tuning of ODFMs by proposing a novel method using heterogeneous low-rank approximations (LoRAs), namely HetLoRA. First, we show that the naive approach of using homogeneous LoRA ranks across devices face a trade-off between overfitting and slow convergence, and thus propose HetLoRA, which allows heterogeneous ranks across client devices and efficiently aggregates and distributes these heterogeneous LoRA modules. By applying rank self-pruning locally and sparsity-weighted aggregation at the server, HetLoRA combines the advantages of high and low-rank LoRAs, which achieves improved convergence speed and final performance compared to homogeneous LoRA. Furthermore, HetLoRA offers enhanced computation efficiency compared to full fine-tuning, making it suitable for federated fine-tuning across heterogeneous devices.
format Preprint
id arxiv_https___arxiv_org_abs_2401_06432
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models
Cho, Yae Jee
Liu, Luyang
Xu, Zheng
Fahrezi, Aldi
Joshi, Gauri
Machine Learning
Distributed, Parallel, and Cluster Computing
Foundation models (FMs) adapt well to specific domains or tasks with fine-tuning, and federated learning (FL) enables the potential for privacy-preserving fine-tuning of the FMs with on-device local data. For federated fine-tuning of FMs, we consider the FMs with small to medium parameter sizes of single digit billion at maximum, referred to as on-device FMs (ODFMs) that can be deployed on devices for inference but can only be fine-tuned with parameter efficient methods. In our work, we tackle the data and system heterogeneity problem of federated fine-tuning of ODFMs by proposing a novel method using heterogeneous low-rank approximations (LoRAs), namely HetLoRA. First, we show that the naive approach of using homogeneous LoRA ranks across devices face a trade-off between overfitting and slow convergence, and thus propose HetLoRA, which allows heterogeneous ranks across client devices and efficiently aggregates and distributes these heterogeneous LoRA modules. By applying rank self-pruning locally and sparsity-weighted aggregation at the server, HetLoRA combines the advantages of high and low-rank LoRAs, which achieves improved convergence speed and final performance compared to homogeneous LoRA. Furthermore, HetLoRA offers enhanced computation efficiency compared to full fine-tuning, making it suitable for federated fine-tuning across heterogeneous devices.
title Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2401.06432