Learning Like Humans: Resource-Efficient Federated Fine-Tuning through Cognitive Developmental Stages

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Yebo, Li, Jingguang, Guo, Zhijiang, Li, Li
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908474896547840
author Wu, Yebo
Li, Jingguang
Guo, Zhijiang
Li, Li
author_facet Wu, Yebo
Li, Jingguang
Guo, Zhijiang
Li, Li
contents Federated fine-tuning enables Large Language Models (LLMs) to adapt to downstream tasks while preserving data privacy, but its resource-intensive nature limits deployment on edge devices. In this paper, we introduce Developmental Federated Tuning (DevFT), a resource-efficient approach inspired by cognitive development that progressively builds a powerful LLM from a compact foundation. DevFT decomposes the fine-tuning process into developmental stages, each optimizing submodels with increasing parameter capacity. Knowledge from earlier stages transfers to subsequent submodels, providing optimized initialization parameters that prevent convergence to local minima and accelerate training. This paradigm mirrors human learning, gradually constructing comprehensive knowledge structure while refining existing skills. To efficiently build stage-specific submodels, DevFT introduces deconfliction-guided layer grouping and differential-based layer fusion to distill essential information and construct representative layers. Evaluations across multiple benchmarks demonstrate that DevFT significantly outperforms state-of-the-art methods, achieving up to 4.59$\times$ faster convergence, 10.67$\times$ reduction in communication overhead, and 9.07% average performance improvement, while maintaining compatibility with existing approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00041
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Like Humans: Resource-Efficient Federated Fine-Tuning through Cognitive Developmental Stages
Wu, Yebo
Li, Jingguang
Guo, Zhijiang
Li, Li
Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Federated fine-tuning enables Large Language Models (LLMs) to adapt to downstream tasks while preserving data privacy, but its resource-intensive nature limits deployment on edge devices. In this paper, we introduce Developmental Federated Tuning (DevFT), a resource-efficient approach inspired by cognitive development that progressively builds a powerful LLM from a compact foundation. DevFT decomposes the fine-tuning process into developmental stages, each optimizing submodels with increasing parameter capacity. Knowledge from earlier stages transfers to subsequent submodels, providing optimized initialization parameters that prevent convergence to local minima and accelerate training. This paradigm mirrors human learning, gradually constructing comprehensive knowledge structure while refining existing skills. To efficiently build stage-specific submodels, DevFT introduces deconfliction-guided layer grouping and differential-based layer fusion to distill essential information and construct representative layers. Evaluations across multiple benchmarks demonstrate that DevFT significantly outperforms state-of-the-art methods, achieving up to 4.59$\times$ faster convergence, 10.67$\times$ reduction in communication overhead, and 9.07% average performance improvement, while maintaining compatibility with existing approaches.
title Learning Like Humans: Resource-Efficient Federated Fine-Tuning through Cognitive Developmental Stages
topic Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2508.00041