paper-with-me

홈 › Papers

Assortment of Attention Heads: Accelerating Federated PEFT with Head Pruning and Strategic Client Selection

2025-05-31 · Yeshwanth Venkatesha, Souvik Kundu, Priyadarshini Panda

Parameter Efficient Fine-Tuning (PEFT) has become the de-facto approach in adapting Large Language Models (LLMs) for downstream tasks in Natural Language Processing. However, its adoption in privacy-preserving distributed learning frameworks, such as Federated Learning (FL), remains relatively limited. This is mainly due to challenges specific to FL, such as resource-constrained devices and diverse data distributions among clients. In this paper, we propose an efficient method to perform PEFT within the FL framework for Multi-Head Attention (MHA) based language models. We address the challenges through head pruning, a novel head-specific weighted aggregation mechanism, and a client selection strategy. Head pruning minimizes training complexity within the clients, guided by the importance score computed based on the confidence of the attention head. Weighted aggregation of heads ensures the global model captures crucial updates from diverse clients complementing our client selection strategy. We show results on the MultiNLI benchmark along with 20 Newsgroups, XL-Sum, and E2E NLG datasets. We use the MultiNLI dataset and T5-small model with LoRA as our PEFT method, attaining sparsity levels of up to 90%, resulting in a communication advantage of up to 1.8x and a reduction in training OPs of 3.9x while maintaining the accuracy drop under 2%.

📄 PDF Abstract BibTeX arXiv:2506.00743

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learningparameter-efficient fine-tuningPrivacy Preserving

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Pruning 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Three-Pronged Spectral Control for Federated Parameter Efficient Fine Tuning

2026-07-23 · Shiva Raj Pokhrel, Dipsan Bhattarai, Anwar Walid arxiv

Federated parameter-efficient fine-tuning (PEFT) enables communication-efficient adaptation of large pretrained models on decentralized edge data, but it remains fragile under non-IID client heterogeneity. In low-rank ad…

parameter-efficient fine-tuning

Probing the Efficacy of Federated Parameter-Efficient Fine-Tuning of Vision Transformers for Medical Image Classification

2024-07-16 · Naif Alkhunaizi, Faris Almalik, Rouqaiah Al-Refai, Muzammal Naseer 외

With the advent of large pre-trained transformer models, fine-tuning these models for various downstream tasks is a critical problem. Paucity of training data, the existence of data silos, and stringent privacy constrain…

Federated Learningimage-classificationImage ClassificationMedical Image Classification+2

Hypernetwork-Driven Low-Rank Adaptation Across Attention Heads

2025-10-05 · Nghiem T. Diep, Dung Le, Tuan Truong, Tan Dinh 외 arxiv

Parameter-efficient fine-tuning (PEFT) has emerged as a powerful paradigm for adapting large-scale pre-trained models to downstream tasks with minimal additional parameters. Among PEFT methods, Low-Rank Adaptation (LoRA)…

parameter-efficient fine-tuning

Optimizing Multimodal Language Models through Attention-based Interpretability

2025-11-28 · Alexander Sergeev, Evgeny Kotelnikov arxiv

Modern large language models become multimodal, analyzing various data formats like text and images. While fine-tuning is effective for adapting these multimodal language models (MLMs) to downstream tasks, full fine-tuni…

parameter-efficient fine-tuningImage Captioning

Dual Attention Heads for Personalized Federated Learning in ECG Classification

2026-07-07 · Kien Le, Joseph Lindley, Quoc Bao Phan, Tuy Tan Nguyen arxiv

Federated learning (FL) enables collaborative model training across institutions without sharing sensitive patient data. However, the inherent heterogeneity of electrocardiogram (ECG) data across healthcare providers pre…

Personalized Federated LearningECG Classification