FedNS: Improving Federated Learning for collaborative image classification on mobile clients

01/20/2021

∙

Federated Learning (FL) is a paradigm that aims to support loosely connected clients in learning a global model collaboratively with the help of a centralized server. The most popular FL algorithm is Federated Averaging (FedAvg), which is based on taking weighted average of the client models, with the weights determined largely based on dataset sizes at the clients. In this paper, we propose a new approach, termed Federated Node Selection (FedNS), for the server's global model aggregation in the FL setting. FedNS filters and re-weights the clients' models at the node/kernel level, hence leading to a potentially better global model by fusing the best components of the clients. Using collaborative image classification as an example, we show with experiments from multiple datasets and networks that FedNS can consistently achieve improved performance over FedAvg.

READ FULL TEXT

FedNS: Improving Federated Learning for collaborative image classification on mobile clients

To Federate or Not To Federate: Incentivizing Client Participation in Federated Learning

Game of Gradients: Mitigating Irrelevant Clients in Federated Learning

Gradient Masked Averaging for Federated Learning

Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning

Learning Private Neural Language Modeling with Attentive Aggregation

M3FGM:a node masking and multi-granularity message passing-based federated graph model for spatial-temporal data prediction

Multimodal Multiple Federated Feature Construction Method for IoT Environments

FedNS: Improving Federated Learning for collaborative image classification on mobile clients

Related Research

To Federate or Not To Federate: Incentivizing Client Participation in Federated Learning

Game of Gradients: Mitigating Irrelevant Clients in Federated Learning

Gradient Masked Averaging for Federated Learning

Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning

Learning Private Neural Language Modeling with Attentive Aggregation

M3FGM:a node masking and multi-granularity message passing-based federated graph model for spatial-temporal data prediction

Multimodal Multiple Federated Feature Construction Method for IoT Environments