Performance Measurement of Federated Learning on Imbalanced Data
Authors:
- 30 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
AI often suffers from getting imbalanced data distribution as unequal samples in classes which will increase the bias of machine learning algorithms. This research aimed to study effects of skew data distribution towards development of data rebalancing on Federated learning (FL) in the future. This research sets left skewed distribution, right skewed distribution and symmetric distribution on Modified National Institute of Standards and Technology database (MNIST) to operate on Convolutional neural network (CNN) in FL mechanism. Then, FL’s performance for working on these imbalanced distributions was tested. Results showed that in overview, the symmetric, left skewed, and right skewed distribution were not different in accuracy but theses imbalanced distributions were different in accuracy from the balanced distribution which has equal samples in all classes at significant level of.05. Standard deviation (SD) of data distribution was directly correlated with FL’s accuracy in high level.Keywords
This publication has 14 references indexed in Scilit:
- diffGrad: An Optimization Method for Convolutional Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2019
- Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks2019
- Deep Learning Techniques for Medical Image Segmentation: Achievements and ChallengesJournal of Digital Imaging, 2019
- Approaches to address the data skew problem in federated learning2019
- A Performance Evaluation of Federated Learning Algorithms2018
- Improved SMOTE Algorithm to Deal with Imbalanced Activity Classes in Smart HomesNeural Processing Letters, 2018
- Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning2005
- SMOTE: Synthetic Minority Over-sampling TechniqueJournal of Artificial Intelligence Research, 2002
- Comparing measures of sample skewness and kurtosisJournal of the Royal Statistical Society: Series D (The Statistician), 1998
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998