paper-with-me

홈 › Papers

FedFT: Improving Communication Performance for Federated Learning with Frequency Space Transformation

2024-09-08 · Chamath Palihawadana, Nirmalie Wiratunga, Anjana Wijekoon, Harsha Kalutarage

Communication efficiency is a widely recognised research problem in Federated Learning (FL), with recent work focused on developing techniques for efficient compression, distribution and aggregation of model parameters between clients and the server. Particularly within distributed systems, it is important to balance the need for computational cost and communication efficiency. However, existing methods are often constrained to specific applications and are less generalisable. In this paper, we introduce FedFT (federated frequency-space transformation), a simple yet effective methodology for communicating model parameters in a FL setting. FedFT uses Discrete Cosine Transform (DCT) to represent model parameters in frequency space, enabling efficient compression and reducing communication overhead. FedFT is compatible with various existing FL methodologies and neural architectures, and its linear property eliminates the need for multiple transformations during federated aggregation. This methodology is vital for distributed solutions, tackling essential challenges like data privacy, interoperability, and energy efficiency inherent to these environments. We demonstrate the generalisability of the FedFT methodology on four datasets using comparative studies with three state-of-the-art FL baselines (FedAvg, FedProx, FedSim). Our results demonstrate that using FedFT to represent the differences in model parameters between communication rounds in frequency space results in a more compact representation compared to representing the entire model in frequency space. This leads to a reduction in communication overhead, while keeping accuracy levels comparable and in some cases even improving it. Our results suggest that this reduction can range from 5% to 30% per client, depending on dataset.

📄 PDF Abstract BibTeX arXiv:2409.05242

Code (1)

chamathpali/fedft 공식 구현

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

Discrete Cosine Transform Discrete Cosine Transform (DCT) is an orthogonal transformation method that decomposes an image to its spatial frequency spectrum. It expresses a finite sequence of data…

Similar Papers 제목 키워드 기반

Adaptive Parameter-Efficient Federated Fine-Tuning on Heterogeneous Devices

2024-12-28 · Jun Liu, Yunming Liao, Hongli Xu, Yang Xu 외

Federated fine-tuning (FedFT) has been proposed to fine-tune the pre-trained language models in a distributed manner. However, there are two critical challenges for efficient FedFT in practical applications, i.e., resour…

parameter-efficient fine-tuning

Federated Low-Rank Adaptation with Differential Privacy over Wireless Networks

2024-11-12 · Tianqu Kang, Zixin Wang, Hengtao He, Jun Zhang 외

Fine-tuning large pre-trained foundation models (FMs) on distributed edge devices presents considerable computational and privacy challenges. Federated fine-tuning (FedFT) mitigates some privacy issues by facilitating co…

Federated Learningparameter-efficient fine-tuning

Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning

2022-03-17 · CVPR 2022 1 · Lin Zhang, Li Shen, Liang Ding, DaCheng Tao 외

Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. Data heterogeneity is one of the main challenges in FL, which results in slow convergence and degraded performance. Most exis…

Data-free Knowledge DistillationFederated LearningKnowledge Distillation

Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning

2025-06-06 · Yujia Huo, Jianchun Liu, Hongli Xu, Zhenguo Ma 외

Federated fine-tuning (FedFT) of large language models (LLMs) has emerged as a promising solution for adapting models to distributed data environments while ensuring data privacy. Existing FedFT methods predominantly uti…

parameter-efficient fine-tuning

Federated Learning with Workload Reduction through Partial Training of Client Models and Entropy-Based Data Selection

2024-12-30 · Hongrui Shi, Valentin Radu, Po Yang

With the rapid expansion of edge devices, such as IoT devices, where crucial data needed for machine learning applications is generated, it becomes essential to promote their participation in privacy-preserving Federated…

Federated LearningPrivacy Preserving