Model Segmentation for Storage Efficient Private Federated Learning with Top r Sparsification

12/22/2022

∙

In federated learning (FL) with top r sparsification, millions of users collectively train a machine learning (ML) model locally, using their personal data by only communicating the most significant r fraction of updates to reduce the communication cost. It has been shown that the values as well as the indices of these selected (sparse) updates leak information about the users' personal data. In this work, we investigate different methods to carry out user-database communications in FL with top r sparsification efficiently, while guaranteeing information theoretic privacy of users' personal data. These methods incur considerable storage cost. As a solution, we present two schemes with different properties that use MDS coded storage along with a model segmentation mechanism to reduce the storage cost at the expense of a controllable amount of information leakage, to perform private FL with top r sparsification.

READ FULL TEXT

Model Segmentation for Storage Efficient Private Federated Learning with Top r Sparsification

Private Read-Update-Write with Controllable Information Leakage for Storage-Efficient Federated Learning with Top r Sparsification

Rate-Privacy-Storage Tradeoff in Federated Learning with Top r Sparsification

Information-Theoretically Private Federated Submodel Learning with Storage Constrained Databases

Private Federated Learning with Domain Adaptation

Communication-Efficient Diffusion Strategy for Performance Improvement of Federated Learning with Non-IID Data

Towards Node Liability in Federated Learning: Computational Cost and Network Overhead

Reduce Communication Costs and Preserve Privacy: Prompt Tuning Method in Federated Learning

Model Segmentation for Storage Efficient Private Federated Learning with Top r Sparsification

Related Research

Private Read-Update-Write with Controllable Information Leakage for Storage-Efficient Federated Learning with Top r Sparsification

Rate-Privacy-Storage Tradeoff in Federated Learning with Top r Sparsification

Information-Theoretically Private Federated Submodel Learning with Storage Constrained Databases

Private Federated Learning with Domain Adaptation

Communication-Efficient Diffusion Strategy for Performance Improvement of Federated Learning with Non-IID Data

Towards Node Liability in Federated Learning: Computational Cost and Network Overhead

Reduce Communication Costs and Preserve Privacy: Prompt Tuning Method in Federated Learning