# A Novel Neural Network-Based Federated Learning System for Imbalanced and Non-IID Data

arXiv: https://arxiv.org/abs/2311.10025 · HTML: https://mlsanity.com/paper/2311.10025/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 48 references that are in the map.
- First posted on arXiv 16 Nov 2023.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [The Future of Digital Health with Federated Learning](https://mlsanity.com/paper/2003.08119/) (2020)
- [Federated Optimization: Distributed Machine Learning for On-Device Intelligence](https://mlsanity.com/paper/1610.02527/) (2016)
- [Federated Learning with Matched Averaging](https://mlsanity.com/paper/2002.06440/) (2020)
- [A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection](https://mlsanity.com/paper/1907.09693/) (2019)
- [Personalized Cross-Silo Federated Learning on Non-IID Data](https://mlsanity.com/paper/2007.03797/) (2020)
- [Privacy-preserving Federated Brain Tumour Segmentation](https://mlsanity.com/paper/1910.00962/) (2019)
- [Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges](https://mlsanity.com/paper/2201.08135/) (2022)
- [Memory-aware curriculum federated learning for breast cancer classification](https://mlsanity.com/paper/2107.02504/) (2021)
- [Fed-Sim: Federated Simulation for Medical Imaging](https://mlsanity.com/paper/2009.00668/) (2020)
- [MangoLeafBD: A Comprehensive Image Dataset to Classify Diseased and Healthy Mango Leaves](https://mlsanity.com/paper/2209.02377/) (2022)
- [Differentially private federated deep learning for multi-site medical image segmentation](https://mlsanity.com/paper/2107.02586/) (2021)
- [Deep learning and face recognition: the state of the art](https://mlsanity.com/paper/1902.03524/) (2019)
- [Transformer-Based Deep Learning Model for Stock Price Prediction: A Case Study on Bangladesh Stock Market](https://mlsanity.com/paper/2208.08300/) (2022)
- [Plant Disease Detection using Region-Based Convolutional Neural Network](https://mlsanity.com/paper/2303.09063/) (2023)
- [Feature Engineering in Learning-to-Rank for Community Question Answering Task](https://mlsanity.com/paper/2309.07610/) (2023)

## Built on by (most cited first, 1 of 1)

- [GourNet: A CNN-Based Model for Mango Leaf Disease Detection](https://mlsanity.com/paper/2604.27764/) (2026)

## Abstract (arXiv)

With the growth of machine learning techniques, privacy of data of users has become a major concern. Most of the machine learning algorithms rely heavily on large amount of data which may be collected from various sources. Collecting these data yet maintaining privacy policies has become one of the most challenging tasks for the researchers. To combat this issue, researchers have introduced federated learning, where a prediction model is learnt by ensuring the privacy of data of clients data. However, the prevalent federated learning algorithms possess an accuracy and efficiency trade-off, especially for non-IID data. In this research, we propose a centralized, neural network-based federated learning system. The centralized algorithm incorporates micro-level parallel processing inspired by the traditional mini-batch algorithm where the client devices and the server handle the forward and backward propagation respectively. We also devise a semi-centralized version of our proposed algorithm. This algorithm takes advantage of edge computing for minimizing the load from the central server, where clients handle both the forward and backward propagation while sacrificing the overall train time to some extent. We evaluate our proposed systems on five well-known benchmark datasets and achieve satisfactory performance in a reasonable time across various data distribution settings as compared to some existing benchmark algorithms.