paper-with-me

홈 › Papers

Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization

2020-08-01 · Rui Hu, Yanmin Gong, Yuanxiong Guo

Federated learning (FL) enables distributed agents to collaboratively learn a centralized model without sharing their raw data with each other. However, data locality does not provide sufficient privacy protection, and it is desirable to facilitate FL with rigorous differential privacy (DP) guarantee. Existing DP mechanisms would introduce random noise with magnitude proportional to the model size, which can be quite large in deep neural networks. In this paper, we propose a new FL framework with sparsification-amplified privacy. Our approach integrates random sparsification with gradient perturbation on each agent to amplify privacy guarantee. Since sparsification would increase the number of communication rounds required to achieve a certain target accuracy, which is unfavorable for DP guarantee, we further introduce acceleration techniques to help reduce the privacy cost. We rigorously analyze the convergence of our approach and utilize Renyi DP to tightly account the end-to-end DP guarantee. Extensive experiments on benchmark datasets validate that our approach outperforms previous differentially-private FL approaches in both privacy guarantee and communication efficiency.

📄 PDF Abstract BibTeX arXiv:2008.01558

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy

2024-08-08 · Wei Huo, Changxin Liu, Kemi Ding, Karl Henrik Johansson 외

This paper investigates the use of the cubic-regularized Newton method within a federated learning framework while addressing two major concerns that commonly arise in federated learning: privacy leakage and communicatio…

Federated Learning

Fedward: Flexible Federated Backdoor Defense Framework with Non-IID Data

2023-07-01 · Zekai Chen, Fuyi Wang, Zhiwei Zheng, Ximeng Liu 외

Federated learning (FL) enables multiple clients to collaboratively train deep learning models while considering sensitive local datasets' privacy. However, adversaries can manipulate datasets and upload models by inject…

backdoor defenseClusteringFederated Learning

MedHE: Communication-Efficient Privacy-Preserving Federated Learning with Adaptive Gradient Sparsification for Healthcare

2025-11-12 · Farjana Yesmin arxiv

Healthcare federated learning requires strong privacy guarantees while maintaining computational efficiency across resource-constrained medical institutions. This paper presents MedHE, a novel framework combining adaptiv…

Computational EfficiencyFederated Learning

Clustering-Based Evolutionary Federated Multiobjective Optimization and Learning

2025-04-29 · Chengui Xiao, Songbai Liu

Federated learning enables decentralized model training while preserving data privacy, yet it faces challenges in balancing communication efficiency, model performance, and privacy protection. To address these trade-offs…

ClusteringDiversityFederated LearningMultiobjective Optimization+1

Efficient and Secure Federated Learning for Financial Applications

2023-03-15 · Tao Liu, Zhi Wang, Hui He, Liangliang Lin 외

The conventional machine learning (ML) and deep learning approaches need to share customers' sensitive information with an external credit bureau to generate a prediction model that opens the door to privacy leakage. Thi…

Federated Learning