Learning to Compare: Relation Network for Few-Shot Learning
Client-Edge-Cloud Hierarchical Federated Learning
A Comprehensive Introduction to Label Noise
Client Selection for Federated Learning With Non-IID Data in Mobile Edge Computing
下载链接 0x00 Abstract A main challenge of FL is that the training data are usually non-Independent, Identically Distributed (non-IID) on the clients, which may bring the biases in the model training and cause possible accuracy degradation. To address this issue, this paper aims to propose a novel FL algorithm to alleviate the accuracy degradation caused by non-IID data at clients. Firstly, we observe that the clients with different degrees of non-IID data present heterogeneous weight divergence wit ...
Active Federated Learning
下载链接 0x00 ABSTRACT The data on each client is highly variable, so the benefit of training on different clients may differ dramatically. To exploit this we propose Active Federated Learning, where in each round clients are selected not uniformly at random, but with a probability conditioned on the current model and the data on the client to maximize efficiency. Key Words: Active Learning, Federated Learning 0x01 Introduction In this paper we introduce Active Federated Learning (AFL) to preferenti ...
Run time :
Total Count :
Last Push :