Interactive Guiding Sparse Auto-Encoder with Wasserstein Regularization for Efficient Classification
In the era of big data, feature engineering has proved its efficiency and importance in dimensionality reduction and useful information extraction from original features. Feature engineering can be expressed as dimensionality reduction and is divided into two types of methods, namely, feature select...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/12/7055 |
| _version_ | 1797596279106174976 |
|---|---|
| author | Haneum Lee Cheonghwan Hur Bunyodbek Ibrokhimov Sanggil Kang |
| author_facet | Haneum Lee Cheonghwan Hur Bunyodbek Ibrokhimov Sanggil Kang |
| author_sort | Haneum Lee |
| collection | DOAJ |
| description | In the era of big data, feature engineering has proved its efficiency and importance in dimensionality reduction and useful information extraction from original features. Feature engineering can be expressed as dimensionality reduction and is divided into two types of methods, namely, feature selection and feature extraction. Each method has its pros and cons. There are a lot of studies that combine these methods. The sparse autoencoder (SAE) is a representative deep feature learning method that combines feature selection with feature extraction. However, existing SAEs do not consider feature importance during training. It causes extracting irrelevant information. In this paper, we propose an interactive guiding sparse autoencoder (IGSAE) to guide the information by two interactive guiding layers and sparsity constraints. The interactive guiding layers keep the main distribution using Wasserstein distance, which is a metric of distribution difference, and it suppresses the leverage of guiding features to prevent overfitting. We perform our experiments using four datasets that have different dimensionalities and numbers of samples. The proposed IGSAE method produces a better classification performance compared to other dimensionality reduction methods. |
| first_indexed | 2024-03-11T02:49:16Z |
| format | Article |
| id | doaj.art-f9ae4680355d4153a6354a89594d601a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T02:49:16Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f9ae4680355d4153a6354a89594d601a2023-11-18T09:08:24ZengMDPI AGApplied Sciences2076-34172023-06-011312705510.3390/app13127055Interactive Guiding Sparse Auto-Encoder with Wasserstein Regularization for Efficient ClassificationHaneum Lee0Cheonghwan Hur1Bunyodbek Ibrokhimov2Sanggil Kang3Department of Computer Engineering, Inha University, Inha-ro 100, Michuhol-gu, Incheon 22212, Republic of KoreaDepartment of Computer Engineering, Inha University, Inha-ro 100, Michuhol-gu, Incheon 22212, Republic of KoreaDepartment of Computer Engineering, Inha University, Inha-ro 100, Michuhol-gu, Incheon 22212, Republic of KoreaDepartment of Computer Engineering, Inha University, Inha-ro 100, Michuhol-gu, Incheon 22212, Republic of KoreaIn the era of big data, feature engineering has proved its efficiency and importance in dimensionality reduction and useful information extraction from original features. Feature engineering can be expressed as dimensionality reduction and is divided into two types of methods, namely, feature selection and feature extraction. Each method has its pros and cons. There are a lot of studies that combine these methods. The sparse autoencoder (SAE) is a representative deep feature learning method that combines feature selection with feature extraction. However, existing SAEs do not consider feature importance during training. It causes extracting irrelevant information. In this paper, we propose an interactive guiding sparse autoencoder (IGSAE) to guide the information by two interactive guiding layers and sparsity constraints. The interactive guiding layers keep the main distribution using Wasserstein distance, which is a metric of distribution difference, and it suppresses the leverage of guiding features to prevent overfitting. We perform our experiments using four datasets that have different dimensionalities and numbers of samples. The proposed IGSAE method produces a better classification performance compared to other dimensionality reduction methods.https://www.mdpi.com/2076-3417/13/12/7055dimensionality reductionautoencoderfeature extractionfeature selectionguiding layerregularization |
| spellingShingle | Haneum Lee Cheonghwan Hur Bunyodbek Ibrokhimov Sanggil Kang Interactive Guiding Sparse Auto-Encoder with Wasserstein Regularization for Efficient Classification Applied Sciences dimensionality reduction autoencoder feature extraction feature selection guiding layer regularization |
| title | Interactive Guiding Sparse Auto-Encoder with Wasserstein Regularization for Efficient Classification |
| title_full | Interactive Guiding Sparse Auto-Encoder with Wasserstein Regularization for Efficient Classification |
| title_fullStr | Interactive Guiding Sparse Auto-Encoder with Wasserstein Regularization for Efficient Classification |
| title_full_unstemmed | Interactive Guiding Sparse Auto-Encoder with Wasserstein Regularization for Efficient Classification |
| title_short | Interactive Guiding Sparse Auto-Encoder with Wasserstein Regularization for Efficient Classification |
| title_sort | interactive guiding sparse auto encoder with wasserstein regularization for efficient classification |
| topic | dimensionality reduction autoencoder feature extraction feature selection guiding layer regularization |
| url | https://www.mdpi.com/2076-3417/13/12/7055 |
| work_keys_str_mv | AT haneumlee interactiveguidingsparseautoencoderwithwassersteinregularizationforefficientclassification AT cheonghwanhur interactiveguidingsparseautoencoderwithwassersteinregularizationforefficientclassification AT bunyodbekibrokhimov interactiveguidingsparseautoencoderwithwassersteinregularizationforefficientclassification AT sanggilkang interactiveguidingsparseautoencoderwithwassersteinregularizationforefficientclassification |