paper-with-me

Papers

Sequential Compression Layers for Efficient Federated Learning in Foundational Models

2024-12-09 · Navyansh Mahla, Sunny Gupta, Amit Sethi

Federated Learning (FL) has gained popularity for fine-tuning large language models (LLMs) across multiple nodes, each with its own private data. While LoRA has been widely adopted for parameter efficient federated fine-tuning, recent theoretical and empirical studies highlight its suboptimal performance in the federated learning context. In response, we propose a novel, simple, and more effective parameter-efficient fine-tuning method that does not rely on LoRA. Our approach introduces a small multi-layer perceptron (MLP) layer between two existing MLP layers the up proj (the FFN projection layer following the self-attention module) and down proj within the feed forward network of the transformer block. This solution addresses the bottlenecks associated with LoRA in federated fine tuning and outperforms recent LoRA-based approaches, demonstrating superior performance for both language models and vision encoders.

📄 PDF Abstract BibTeX arXiv:2412.07021

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learningparameter-efficient fine-tuning

Similar Papers 제목 키워드 기반

Toward Efficient Federated Learning in Multi-Channeled Mobile Edge Network with Layerd Gradient Compression

2021-09-18 · Haizhou Du, Xiaojie Feng, Qiao Xiang, Haoyu Liu

A fundamental issue for federated learning (FL) is how to achieve optimal model performance under highly dynamic communication environments. This issue can be alleviated by the fact that modern edge devices usually can c…

Federated Learning

Entropy-Guided Tensor Compression for Multimodal Federated Learning on Edge Devices

2026-07-07 · Quoc Bao Phan, Tuy Tan Nguyen arxiv

Federated learning (FL) over mobile and edge devices increasingly involves multimodal models in which clients differ in both sensing capability and computational capacity. Existing update compression schemes typically ap…

Federated Learning

Communication-Efficient Federated Learning via Quantized Compressed Sensing

2021-11-30 · Yongjeong Oh, Namyoon Lee, Yo-Seb Jeon, H. Vincent Poor

In this paper, we present a communication-efficient federated learning framework inspired by quantized compressed sensing. The presented framework consists of gradient compression for wireless devices and gradient recons…

compressed sensingFederated LearningQuantization

Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights

2025-09-05 · Cosmin-Andrei Hatfaludi, Alex Serban arxiv

Federated learning has the potential to unlock siloed data and distributed resources by enabling collaborative model training without sharing private data. As more complex foundational models gain widespread use, the nee…

Self-Supervised LearningFederated LearningTransfer Learning

EdgeFLow: Serverless Federated Learning via Sequential Model Migration in Edge Networks

2026-03-03 · Yuchen Shi, Qijun Hou, Pingyi Fan, Khaled B. Letaief arxiv

Federated Learning (FL) has emerged as a transformative distributed learning paradigm in the era of Internet of Things (IoT), reconceptualizing data processing methodologies. However, FL systems face significant communic…

Federated Learning