Litcius/Paper detail

Federated Learning with Class Imbalance Reduction

Miao Yang, Ximin Wang, Hongbin Zhu, Haifeng Wang, Hua Qian

20212021 29th European Signal Processing Conference (EUSIPCO)127 citationsDOI

Abstract

Federated learning (FL) is a promising technique that enables a large amount of edge computing devices to collaboratively train a global learning model. Due to the communication limitation, only a subset of devices can be engaged to train and transmit the trained model to centralized server for aggregation. Since the local data distribution varies among all devices, class imbalance problem arises along with the unfavorable client selection, resulting in a slow converge rate of the global model. In this paper, we design an estimation scheme to reveal the class distribution without the awareness of raw data. According to the estimation scheme, we propose a multi-arm bandit based algorithm that can select the client set with minimal class imbalance. The proposed algorithm can significantly improve the convergence performance of the global model. Simulation results demonstrate the effectiveness of the proposed algorithm.

Topics & Concepts

Computer scienceScheme (mathematics)Convergence (economics)Class (philosophy)Reduction (mathematics)Enhanced Data Rates for GSM EvolutionSet (abstract data type)Rate of convergenceServerRaw dataSelection (genetic algorithm)Edge computingArtificial intelligenceComputer networkMathematicsChannel (broadcasting)EconomicsGeometryMathematical analysisEconomic growthProgramming languagePrivacy-Preserving Technologies in DataIoT and Edge/Fog ComputingCOVID-19 diagnosis using AI
Federated Learning with Class Imbalance Reduction | Litcius