paper-with-me

Papers

FedMPDD: Communication-Efficient Federated Learning with Privacy Preservation Attributes via Projected Directional Derivative

2025-12-23 · Mohammadreza Rostami, Solmaz S. Kia arxiv

This paper introduces \texttt{FedMPDD} (\textbf{Fed}erated Learning via \textbf{M}ulti-\textbf{P}rojected \textbf{D}irectional \textbf{D}erivatives), a novel algorithm that simultaneously optimizes bandwidth utilization and enhances privacy in Federated Learning. The core idea of \texttt{FedMPDD} is to encode each client's high-dimensional gradient by computing its directional derivatives along multiple random vectors. This compresses the gradient into a much smaller message, significantly reducing uplink communication costs from $\mathcal{O}(d)$ to $\mathcal{O}(m)$, where $m \ll d$. The server then decodes the aggregated information by projecting it back onto the same random vectors. Our key insight is that averaging multiple projections overcomes the dimension-dependent convergence limitations of a single projection. We provide a rigorous theoretical analysis, establishing that \texttt{FedMPDD} converges at a rate of $\mathcal{O}(1/\sqrt{K})$, matching the performance of FedSGD. Furthermore, we demonstrate that our method provides some inherent privacy against gradient inversion attacks due to the geometric properties of low-rank projections, offering a tunable privacy-utility trade-off controlled by the number of projections. Extensive experiments on benchmark datasets validate our theory and demonstrates our results.

📄 PDF Abstract BibTeX arXiv:2512.20814

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

FedREP: A Byzantine-Robust, Communication-Efficient and Privacy-Preserving Framework for Federated Learning

2023-03-09 · Yi-Rui Yang, Kun Wang, Wu-Jun Li

Federated learning (FL) has recently become a hot research topic, in which Byzantine robustness, communication efficiency and privacy preservation are three important aspects. However, the tension among these three aspec…

Federated LearningPrivacy Preserving

Selective Attention Federated Learning: Improving Privacy and Efficiency for Clinical Text Classification

2025-04-16 · Yue Li, Lihong Zhang

Federated Learning (FL) faces major challenges regarding communication overhead and model privacy when training large language models (LLMs), especially in healthcare applications. To address these, we introduce Selectiv…

Clinical Concept ExtractionFederated Learningtext-classificationText Classification

Communication-Learning Co-Design for Differentially Private Over-the-Air Federated Distillation

2025-08-06 · Zihao Hu, Jia Yan, Ying-Jun Angela Zhang arxiv

The ever-growing learning model size nowadays challenges the communication efficiency and privacy preservation of the traditional federated learning (FL). In this paper, we propose a novel differentially private (DP) ove…

Federated Learning

Private and Communication-Efficient Federated Learning based on Differentially Private Sketches

2024-10-08 · Meifan Zhang, Zhanhong Xie, Lihua Yin

Federated learning (FL) faces two primary challenges: the risk of privacy leakage due to parameter sharing and communication inefficiencies. To address these challenges, we propose DPSFL, a federated learning method that…

Federated Learning

A Federated Deep Learning Framework for Privacy Preservation and Communication Efficiency

2020-01-22 · Tien-Dung Cao, Tram Truong-Huu, Hien Tran, Khanh Tran

Deep learning has achieved great success in many applications. However, its deployment in practice has been hurdled by two issues: the privacy of data that has to be aggregated centrally for model training and high commu…

Federated LearningPrivacy Preserving