Fair Rewards in Federated Learning: A Novel Approach with Adjusted OR-TMC Shapley Value Approximation Algorithm
Journal: International Journal of Advanced Trends in Computer Science and Engineering (IJATCSE) (Vol.12, No. 4)Publication Date: 2023-08-14
Authors : Reem Alshahrani;
Page : 202-219
Keywords : Federated Learning; Machine Learning; One Round Model Reconstruction; Shapley Values; Truncated Monte Carlo Shapley;
Abstract
Federated Learning (FL), a new private and secure Machine Learning (ML) approach, faces a big difficulty when it comes to sharing profits with data producers. Shapley Values (SV) have been proposed as a fair incentive system to remedy this, but it is challenging to determine the SV with accuracy. Therefore, SV calculation is problematic since the number of necessary federated models rises exponentially with the number of data sources. As a result, an effective approximation approach is required. The One Round Model Reconstruction (OR) and Truncated Monte Carlo Shapley (TMC) approaches for SV approximation in FL are being improved and combined in this study. The proposed approach, Adjusted OR-TMC, combines TMC principles with OR and achieves a comparable level of accuracy over a shorter period. Because of this, Adjusted OR-TMC is the perfect OR replacement. The performance outcomes and underlying causes are covered in the study.
Other Latest Articles
- Recognition of Hindi Character Using OCR-Technology: A Review
- Public Feedback on the Programs and Services of Municipal Health Office of Padada through Sentiment Analysis using Convolutional Neural Network
- Designing and Analysis of an Architecture of Motion Control for a Mobile Robot Using Simulation
- Data Protection in IoT using CoAP based on Enhanced DTLS
- Satellite Data for Forest Fire Detection using Deep learning
Last modified: 2023-08-15 19:04:55