Hierarchical fuzzy neural networks with privacy preservation for heterogeneous big data
This work addresses privacy preservation in machine learning for heterogeneous big data, which is an incremental improvement over existing methods.
The paper tackles the challenges of heterogeneous big data, including scale, dimensionality, uncertainty, and privacy concerns, by proposing a privacy-preserving hierarchical fuzzy neural network (PP-HFNN) that uses a two-stage optimization algorithm for scalable and fast training without gradient vanishing issues.
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.