A new Stack Autoencoder: Neighbouring Sample Envelope Embedded Stack Autoencoder Ensemble Model

TL;DR

This paper introduces NE_ESAE, a novel deep autoencoder model that incorporates hierarchical structural information of samples through envelope learning, improving feature learning and classification performance.

Contribution

The paper proposes a new SAE model with a neighboring sample envelope mechanism and multilayer sample spaces, enhancing deep feature extraction by considering sample relationships.

Findings

Outperforms traditional feature learning methods.

Achieves better classification accuracy on public datasets.

Effectively captures hierarchical structural information.

Abstract

Stack autoencoder (SAE), as a representative deep network, has unique and excellent performance in feature learning, and has received extensive attention from researchers. However, existing deep SAEs focus on original samples without considering the hierarchical structural information between samples. To address this limitation, this paper proposes a new SAE model-neighbouring envelope embedded stack autoencoder ensemble (NE_ESAE). Firstly, the neighbouring sample envelope learning mechanism (NSELM) is proposed for preprocessing of input of SAE. NSELM constructs sample pairs by combining neighbouring samples. Besides, the NSELM constructs a multilayer sample spaces by multilayer iterative mean clustering, which considers the similar samples and generates layers of envelope samples with hierarchical structural information. Second, an embedded stack autoencoder (ESAE) is proposed and trained in each layer of sample space to consider the original samples during training and in the network structure, thereby better finding the relationship between original feature samples and deep feature samples. Third, feature reduction and base classifiers are conducted on the layers of envelope samples respectively, and output classification results of every layer of samples. Finally, the classification results of the layers of envelope sample space are fused through the ensemble mechanism. In the experimental section, the proposed algorithm is validated with over ten representative public datasets. The results show that our method significantly has better performance than existing traditional feature learning methods and the representative deep autoencoders.