Adaptive Local Steps Federated Learning with Differential Privacy Driven by Convergence Analysis: Paper and Code

Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Adaptive Local Steps Federated Learning with Differential Privacy Driven by Convergence Analysis

Aug 21, 2023
Xinpeng Ling, Jie Fu, Zhili Chen

Figure 1 for Adaptive Local Steps Federated Learning with Differential Privacy Driven by Convergence Analysis

Figure 2 for Adaptive Local Steps Federated Learning with Differential Privacy Driven by Convergence Analysis

Figure 3 for Adaptive Local Steps Federated Learning with Differential Privacy Driven by Convergence Analysis

Figure 4 for Adaptive Local Steps Federated Learning with Differential Privacy Driven by Convergence Analysis

Share this with someone who'll enjoy it:

Federated Learning (FL) is a distributed machine learning technique that allows model training among multiple devices or organizations without sharing data. However, while FL ensures that the raw data is not directly accessible to external adversaries, adversaries can still obtain some statistical information about the data through differential attacks. Differential Privacy (DP) has been proposed, which adds noise to the model or gradients to prevent adversaries from inferring private information from the transmitted parameters. We reconsider the framework of differential privacy federated learning in resource-constrained scenarios (privacy budget and communication resources). We analyze the convergence of federated learning with differential privacy (DPFL) on resource-constrained scenarios and propose an Adaptive Local Steps Differential Privacy Federated Learning (ALS-DPFL) algorithm. We experiment our algorithm on the FashionMNIST and Cifar-10 datasets and achieve quite good performance relative to previous work.

View paper on

Share this with someone who'll enjoy it: