paper-with-me

Papers

MUFFLe: Efficient Model Update Compression via Generalized Deduplication for Federated Learning

2026-06-12 · Xiaobo Zhao, Daniel E. Lucani arxiv

Federated learning is well suited to edge environments but is often limited by the uplink cost of transmitting model updates. This Work-in-Progress paper presents MUFFLe, a communication-efficient update compression scheme that integrates generalized deduplication (GD) into the FedAvg pipeline. MUFFLe deduplicates repeated patterns across the update vector, yielding a fixed-rate, variable-count compression scheme. Preliminary experiments on IID MNIST with 20 clients show that MUFFLe reaches the target accuracy of $92.93\%$ with 38~MB cumulative uplink communication, compared with 75~MB for 8-bit quantization, 86~MB for Top-$k$ sparsification, and 310~MB for uncompressed FedAvg. These results demonstrate the feasibility of applying GD to communication-efficient federated learning.

📄 PDF Abstract BibTeX arXiv:2606.14354

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language Models (Extended Version)

2024-07-11 · Aydin Abadi, Vishnu Asutosh Dasu, Sumanta Sarkar

Deduplication is a vital preprocessing step that enhances machine learning model performance and saves training time and energy. However, enhancing federated learning through deduplication poses challenges, especially re…

Federated LearningPrivacy Preserving

DeepSketch: A New Machine Learning-Based Reference Search Technique for Post-Deduplication Delta Compression

2022-02-17 · Jisung Park, Jeoggyun Kim, Yeseong Kim, Sungjin Lee 외

Data reduction in storage systems is becoming increasingly important as an effective solution to minimize the management cost of a data center. To maximize data-reduction efficiency, existing post-deduplication delta-com…

Management

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

RAGE for the Machine: Image Compression with Low-Cost Random Access for Embedded Applications

2024-02-07 · Christian D. Rask, Daniel E. Lucani

We introduce RAGE, an image compression framework that achieves four generally conflicting objectives: 1) good compression for a wide variety of color images, 2) computationally efficient, fast decompression, 3) fast ran…

Image Compression

Muffled Semi-Supervised Learning

2016-05-28 · Akshay Balsubramani, Yoav Freund

We explore a novel approach to semi-supervised learning. This approach is contrary to the common approach in that the unlabeled examples serve to "muffle," rather than enhance, the guidance provided by the labeled exampl…

regression