Redirigiendo al acceso original de articulo en 19 segundos...
Inicio  /  Future Internet  /  Vol: 14 Par: 12 (2022)  /  Artículo
ARTÍCULO
TITULO

FedCO: Communication-Efficient Federated Learning via Clustering Optimization

Ahmed A. Al-Saedi    
Veselka Boeva and Emiliano Casalicchio    

Resumen

Federated Learning (FL) provides a promising solution for preserving privacy in learning shared models on distributed devices without sharing local data on a central server. However, most existing work shows that FL incurs high communication costs. To address this challenge, we propose a clustering-based federated solution, entitled Federated Learning via Clustering Optimization (FedCO), which optimizes model aggregation and reduces communication costs. In order to reduce the communication costs, we first divide the participating workers into groups based on the similarity of their model parameters and then select only one representative, the best performing worker, from each group to communicate with the central server. Then, in each successive round, we apply the Silhouette validation technique to check whether each representative is still made tight with its current cluster. If not, the representative is either moved into a more appropriate cluster or forms a cluster singleton. Finally, we use split optimization to update and improve the whole clustering solution. The updated clustering is used to select new cluster representatives. In that way, the proposed FedCO approach updates clusters by repeatedly evaluating and splitting clusters if doing so is necessary to improve the workers? partitioning. The potential of the proposed method is demonstrated on publicly available datasets and LEAF datasets under the IID and Non-IID data distribution settings. The experimental results indicate that our proposed FedCO approach is superior to the state-of-the-art FL approaches, i.e., FedAvg, FedProx, and CMFL, in reducing communication costs and achieving a better accuracy in both the IID and Non-IID cases.

 Artículos similares

       
 
Georg Gartner, Olesia Ignateva, Bibigul Zhunis and Johanna Pühringer    
Maps are the culmination of numerous choices, with many offering multiple alternatives. Not all of these choices are inherently guided by default, clarity, or universally accepted best practices, guidelines, or recommendations. In the realm of cartograph... ver más

 
Alvaro A. Teran-Quezada, Victor Lopez-Cabrera, Jose Carlos Rangel and Javier E. Sanchez-Galan    
Convolutional neural networks (CNN) have provided great advances for the task of sign language recognition (SLR). However, recurrent neural networks (RNN) in the form of long?short-term memory (LSTM) have become a means for providing solutions to problem... ver más

 
Emanuele Santonicola, Ennio Andrea Adinolfi, Simone Coppola and Francesco Pascale    
Nowadays, a vehicle can contain from 20 to 100 ECUs, which are responsible for ordering, controlling and monitoring all the components of the vehicle itself. Each of these units can also send and receive information to other units on the network or exter... ver más
Revista: Future Internet

 
Adwitiya Mukhopadhyay, Aryadevi Remanidevi Devidas, Venkat P. Rangan and Maneesha Vinodini Ramesh    
Addressing the inadequacy of medical facilities in rural communities and the high number of patients affected by ailments that need to be treated immediately is of prime importance for all countries. The various recent healthcare emergency situations bri... ver más
Revista: Future Internet

 
Radheshyam Singh, Leo Mendiboure, José Soler, Michael Stübert Berger, Tidiane Sylla, Marion Berbineau and Lars Dittmann    
In the near future, there will be a greater emphasis on sharing network resources between roads and railways to improve transportation efficiency and reduce infrastructure costs. This could enable the development of global Cooperative Intelligent Transpo... ver más
Revista: Future Internet