MUFFLe: Efficient Model Update Compression via Generalized Deduplication for Federated Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language Models (Extended Version)
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 PreservingDeepSketch: A New Machine Learning-Based Reference Search Technique for Post-Deduplication Delta Compression
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…
ManagementCommunication-Efficient Federated Learning via Quantized Compressed Sensing
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 LearningQuantizationRAGE for the Machine: Image Compression with Low-Cost Random Access for Embedded Applications
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 CompressionMuffled Semi-Supervised Learning
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