# Hierarchical fuzzy neural networks with privacy preservation for heterogeneous big data

arXiv: https://arxiv.org/abs/2209.08467 · HTML: https://mlsanity.com/paper/2209.08467/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 60 references that are in the map.
- First posted on arXiv 18 Sep 2022.

## Builds on (most cited first, 6 of 6)

- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Global Convergence of ADMM in Nonconvex Nonsmooth Optimization](https://mlsanity.com/paper/1511.06324/) (2015)
- [Phase Retrieval using Alternating Minimization](https://mlsanity.com/paper/1306.0160/) (2013)
- [Fast Training Algorithms for Deep Convolutional Fuzzy Systems with Application to Stock Index Prediction](https://mlsanity.com/paper/1812.11226/) (2018)
- [Decentralized Multi-Task Learning Based on Extreme Learning Machines](https://mlsanity.com/paper/1904.11366/) (2019)
- [A Novel Anomaly Detection Algorithm for Hybrid Production Systems based on Deep Learning and Timed Automata](https://mlsanity.com/paper/2010.15415/) (2020)

## Built on by (most cited first, 3 of 3)

- [FedTP: Federated Learning by Transformer Personalization](https://mlsanity.com/paper/2211.01572/) (2022)
- [Federated Fuzzy Neural Network with Evolutionary Rule Learning](https://mlsanity.com/paper/2210.14393/) (2022)
- [Cross Task Neural Architecture Search for EEG Signal Classifications](https://mlsanity.com/paper/2210.06298/) (2022)

## Abstract (arXiv)

Heterogeneous big data poses many challenges in machine learning. Its enormous scale, high dimensionality, and inherent uncertainty make almost every aspect of machine learning difficult, from providing enough processing power to maintaining model accuracy to protecting privacy. However, perhaps the most imposing problem is that big data is often interspersed with sensitive personal data. Hence, we propose a privacy-preserving hierarchical fuzzy neural network (PP-HFNN) to address these technical challenges while also alleviating privacy concerns. The network is trained with a two-stage optimization algorithm, and the parameters at low levels of the hierarchy are learned with a scheme based on the well-known alternating direction method of multipliers, which does not reveal local data to other agents. Coordination at high levels of the hierarchy is handled by the alternating optimization method, which converges very quickly. The entire training procedure is scalable, fast and does not suffer from gradient vanishing problems like the methods based on back-propagation. Comprehensive simulations conducted on both regression and classification tasks demonstrate the effectiveness of the proposed model.