paper-with-me

홈 › Papers

Personalized Federated Instruction Tuning via Neural Architecture Search

2024-02-26 · Pengyu Zhang, Yingbo Zhou, Ming Hu, Junxian Feng, Jiawen Weng, Mingsong Chen

Federated Instruction Tuning (FIT) has shown the ability to achieve collaborative model instruction tuning among massive data owners without sharing private data. However, it still faces two key challenges, i.e., data and resource heterogeneity. Due to the varying data distribution and preferences among data owners, FIT cannot adapt to the personalized data of individual owners. Moreover, clients with superior computational abilities are constrained since they need to maintain the same fine-tuning architecture as the weaker clients. To address these issues, we propose a novel Personalized Federated Instruction Tuning (PerFIT) framework based on architecture search. Specifically, PerFIT allows each client to search for a personalized architecture by expanding the trainable parameter space of the global model followed by pruning the parameters to the original state. This procedure allows personalized instruction fine-tuning within expanded parameter spaces, concurrently preserving the same number of trainable parameters. Furthermore, to release the abilities of heterogeneous computational resources and enhance the performance of personalization on local data, we exploit personalized parameter-wise aggregation. The evaluation with multiple LLMs non-IID scenarios demonstrates that compared to the state-of-the-art FIT methods, our approach can achieve up to a 23% decrease in perplexity.

📄 PDF Abstract BibTeX arXiv:2402.16919

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Architecture Search

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Personalized Federated Fine-Tuning for LLMs via Data-Driven Heterogeneous Model Architectures

2024-11-28 · YiCheng Zhang, Zhen Qin, Zhaomin Wu, Shuiguang Deng

A large amount of instructional text data is essential to enhance the performance of pre-trained large language models (LLMs) for downstream tasks. This data can contain sensitive information and therefore cannot be shar…

Federated Learning

Personalized Wireless Federated Learning for Large Language Models

2024-04-20 · Feibo Jiang, Li Dong, Siwei Tu, Yubo Peng 외

Large Language Models (LLMs) have revolutionized natural language processing tasks. However, their deployment in wireless networks still face challenges, i.e., a lack of privacy and security protection mechanisms. Federa…

Federated Learning

Pilot: Building the Federated Multimodal Instruction Tuning Framework

2025-01-23 · Baochen Xiong, Xiaoshan Yang, Yaguang Song, YaoWei Wang 외

In this paper, we explore a novel federated multimodal instruction tuning task(FedMIT), which is significant for collaboratively fine-tuning MLLMs on different types of multimodal instruction data on distributed devices.…

General Knowledge

FedLoRA-Optimizer: Federated LoRA Fine-Tuning with Global and Local Optimization in Heterogeneous Data Scenarios

2025-10-13 · Jianzhe Zhao, Hailin Zhu, Yu Zhang, Ziqi Chen 외 arxiv

Federated efficient fine-tuning has emerged as an approach that leverages distributed data and computational resources across nodes to address the challenges of large-scale fine-tuning and privacy preservation. The Low-R…

Dual-Personalizing Adapter for Federated Foundation Models

2024-03-28 · Yiyuan Yang, Guodong Long, Tao Shen, Jing Jiang 외

Recently, foundation models, particularly large language models (LLMs), have demonstrated an impressive ability to adapt to various tasks by fine-tuning diverse instruction data. Notably, federated foundation models (Fed…

Federated Learning