paper-with-me

홈 › Papers

On the Convergence of Zeroth-Order Federated Tuning for Large Language Models

2024-02-08 · Zhenqing Ling, Daoyuan Chen, Liuyi Yao, Yaliang Li, Ying Shen

The confluence of Federated Learning (FL) and Large Language Models (LLMs) is ushering in a new era in privacy-preserving natural language processing. However, the intensive memory requirements for fine-tuning LLMs pose significant challenges, especially when deploying on clients with limited computational resources. To circumvent this, we explore the novel integration of Memory-efficient Zeroth-Order Optimization within a federated setting, a synergy we term as FedMeZO. Our study is the first to examine the theoretical underpinnings of FedMeZO in the context of LLMs, tackling key questions regarding the influence of large parameter spaces on optimization behavior, the establishment of convergence properties, and the identification of critical parameters for convergence to inform personalized federated strategies. Our extensive empirical evidence supports the theory, showing that FedMeZO not only converges faster than traditional first-order methods such as FedAvg but also significantly reduces GPU memory usage during training to levels comparable to those during inference. Moreover, the proposed personalized FL strategy that is built upon the theoretical insights to customize the client-wise learning rate can effectively accelerate loss reduction. We hope our work can help to bridge theoretical and practical aspects of federated fine-tuning for LLMs, thereby stimulating further advancements and research in this area.

📄 PDF Abstract BibTeX arXiv:2402.05926

Code (1)

alibaba/federatedscope 공식 구현 pytorch

Tasks

Federated LearningGPUPrivacy Preserving

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

ZorBA: Zeroth-order Federated Fine-tuning of LLMs with Heterogeneous Block Activation

2026-02-19 · Chuiyang Meng, Ming Tang, Vincent W. S. Wong arxiv

Federated fine-tuning of large language models (LLMs) enables collaborative tuning across distributed clients. However, due to the large size of LLMs, local updates in federated learning (FL) may incur substantial video …

Federated Learning

HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregation

2026-03-16 · Qiyuan Chen, Xian Wu, Yi Wang, Xianhao Chen arxiv

Fine-tuning large models on edge devices is severely hindered by the memory-intensive backpropagation (BP) in standard frameworks like federated learning and split learning. While substituting BP with zeroth-order optimi…

Federated Learning

Reconciling Hessian-Informed Acceleration and Scalar-Only Communication for Efficient Federated Zeroth-Order Fine-Tuning

2025-06-03 · Zhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong 외

Recent dimension-free communication frameworks in Federated Learning (FL), such as DeComFL, significantly reduce per-round communication by transmitting only scalars via zeroth-order stochastic gradient descent (ZO-SGD).…

Federated Learning

FedZeN: Towards superlinear zeroth-order federated learning via incremental Hessian estimation

2023-09-29 · Alessio Maritan, Subhrakanti Dey, Luca Schenato

Federated learning is a distributed learning framework that allows a set of clients to collaboratively train a model under the orchestration of a central server, without sharing raw data samples. Although in many practic…

Federated LearningPrivacy Preserving

Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning

2022-01-24 · Wenzhi Fang, Ziyi Yu, Yuning Jiang, Yuanming Shi 외

Federated learning (FL), as an emerging edge artificial intelligence paradigm, enables many edge devices to collaboratively train a global model without sharing their private data. To enhance the training efficiency of F…

Federated LearningSecond-order methods