paper-with-me

Papers

Practical Locally Private Federated Learning with Communication Efficiency

2021-01-01 · Yan Feng, Tao Xiong, Ruofan Wu, Yuan Qi

Federated learning (FL) is a technique that trains machine learning models from decentralized data sources. We study FL under local differential privacy constraints, which provides strong protection against sensitive data disclosures via obfuscating the data before leaving the client. We identify two major concerns in designing practical privacy-preserving FL algorithms: communication efficiency and high-dimensional compatibility. We then develop a gradient-based learning algorithm called \emph{sqSGD} (selective quantized stochastic gradient descent) that addresses both concerns. The proposed algorithm is based on a novel privacy-preserving quantization scheme that uses a constant number of bits per dimension per client. Then we improve the base algorithm in two ways: first, we apply a gradient subsampling strategy that offers simultaneously better training performance and smaller communication costs under a fixed privacy budget. Secondly, we utilize randomized rotation as a preprocessing step to reduce quantization error. We also initialize a discussion about the role of quantization and perturbation in FL algorithm design with privacy and communication constraints. Finally, the practicality of the proposed framework is demonstrated on benchmark datasets. Experiment results show that sqSGD successfully learns large models like LeNet and ResNet with local privacy constraints. In addition, with fixed privacy and communication level, the performance of sqSGD significantly dominates baselines that do not involve quantization.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningPrivacy PreservingQuantization

Methods 이 논문이 사용한 방법론

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Residual Connection 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Average Pooling 설명 없음

Similar Papers 제목 키워드 기반

FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Models

2024-03-14 · Kai Yi, Georg Meinhardt, Laurent Condat, Peter Richtárik

Federated Learning (FL) has garnered increasing attention due to its unique characteristic of allowing heterogeneous clients to process their private data locally and interact with a central server, while being respectfu…

Federated LearningQuantization

FedSpaLLM: Federated Pruning of Large Language Models

2024-10-18 · Guangji Bai, Yijiang Li, Zilinghan Li, Liang Zhao 외

Large Language Models (LLMs) achieve state-of-the-art performance but are challenging to deploy due to their high computational and storage demands. Pruning can reduce model size, yet existing methods assume public acces…

Federated LearningPrivacy Preserving

Practical and Light-weight Secure Aggregation for Federated Submodel Learning

2021-11-02 · Jamie Cui, Cen Chen, Tiandi Ye, Li Wang

Recently, Niu, et. al. introduced a new variant of Federated Learning (FL), called Federated Submodel Learning (FSL). Different from traditional FL, each client locally trains the submodel (e.g., retrieved from the serve…

Federated LearningPrivacy PreservingRetrieval

sqSGD: Locally Private and Communication Efficient Federated Learning

2022-06-21 · Yan Feng, Tao Xiong, Ruofan Wu, LingJuan Lv 외

Federated learning (FL) is a technique that trains machine learning models from decentralized data sources. We study FL under local notions of privacy constraints, which provides strong protection against sensitive data …

Federated LearningPrivacy PreservingQuantization

LLM-QFL: Distilling Large Language Model for Quantum Federated Learning

2025-05-24 · Dev Gurung, Shiva Raj Pokhrel

Inspired by the power of large language models (LLMs), our research adapts them to quantum federated learning (QFL) to boost efficiency and performance. We propose a federated fine-tuning method that distills an LLM with…

Federated LearningLanguage ModelingLanguage ModellingLarge Language Model