Skip to main content

Research Repository

Advanced Search

A novel ensemble aggregation method based on deep learning representation.

Nguyen, Truong Thanh; Elyan, Eyad; Dang, Truong; Nguyen, Tien Thanh; Longmuir, Martin

Authors

Truong Thanh Nguyen

Martin Longmuir



Contributors

Apostolos Antonacopoulos
Editor

Subhasis Chaudhuri
Editor

Rama Chellappa
Editor

Cheng-Lin Liu
Editor

Saumik Bhattacharya
Editor

Umapada Pal
Editor

Abstract

We propose a novel ensemble aggregation method by using a deep learning-based representation approach. Specifically, we applied the Cross-Validation procedure on training data with a number of learning algorithms to obtain the predictions for training data called meta-data. A neural network model is trained on this meta-data to generate representations associated with class labels. In our method, the neural network model functions as an encoder, learning the relationship between base classifiers' outputs and mapping meta-data to a representation space. The vectors in the mapped space provide a more accurate representation than traditional methods by reducing the distance of vectors in the same class and increasing the distance in different classes. Our method was compared with four well-known ensemble methods: Decision Template, an ensemble with a MultiLayer Perceptron (MLP)-based combiner, gcForest, and XgBoost. Experiments conducted on 20 UCI datasets demonstrate the outstanding performance of our ensemble aggregation method. The results show that our method achieves better delegation of class label representations, enhancing the final results of classification tasks.

Citation

NGUYEN, T.T., ELYAN, E., DANG, T., NGUYEN, T.T. and LONGMUIR, M. 2025. A novel ensemble aggregation method based on deep learning representation. In Antonacopoulos, A., Chaudhuri, S., Chellappa, R., et al. (eds.) Pattern recognition: proceedings of the 27th International conference on pattern recognition, 01-05 December 2024, Kolkata, India. Lecture notes in computer science, 15324. Cham: Springer [online], pages 31-46. Available from: https://doi.org/10.1007/978-3-031-78383-8_3

Presentation Conference Type Conference Paper (published)
Conference Name 27th International conference on pattern recognition, 01-05 December 2024, Kolkata, India
Start Date Dec 1, 2024
End Date Dec 5, 2024
Acceptance Date Aug 20, 2024
Online Publication Date Dec 2, 2024
Publication Date Jan 1, 2025
Deposit Date Dec 19, 2024
Publicly Available Date Dec 3, 2025
Print ISSN 0302-9743
Electronic ISSN 1611-3349
Publisher Springer
Peer Reviewed Peer Reviewed
Pages 31-46
Series Title Lecture notes in computer science (LNCS)
Series Number 15324
Book Title Pattern recognition: proceedings of the 27th International conference on pattern recognition, 01-05 December 2024, Kolkata, India
ISBN 9783031783821
DOI https://doi.org/10.1007/978-3-031-78383-8_3
Keywords Ensemble learning; Ensemble combining; Ensemble aggregation; Multilayer perceptron; Ensemble method
Public URL https://rgu-repository.worktribe.com/output/2625873