Deep active reinforcement learning for privacy preserve data mining in 5G environments
Finding frequent patterns identifies the most important patterns in data sets. Due to the huge and high-dimensional nature of transactional data, classical pattern mining techniques suffer from the limitations of dimensions and data annotations. Recently, data mining while preserving privacy is considered an important research area in recent decades. Information privacy is a tradeoff that must be considered when using data. Through many years, privacy-preserving data mining (PPDM) made use of methods that are mostly based on heuristics. The operation of deletion was used to hide the sensitive information in PPDM. In this study, we used deep active learning to hide sensitive operations and protect private information. This paper combines entropy-based active learning with an attention-based approach to effectively detect sensitive patterns. The constructed models are then validated using high-dimensional transactional data with attention-based and active learning methods in a reinforcement environment. The results show that the proposed model can support and improve the decision boundaries by increasing the number of training instances through the use of a pooling technique and an entropy uncertainty measure. The proposed paradigm can achieve cleanup by hiding sensitive items and avoiding non-sensitive items. The model outperforms greedy, genetic, and particle swarm optimization approaches.