Relational autoencoder for feature extraction

By Qinxue Meng, Daniel R. Catchpoole, D. Skillicom, Paul J. Kennedy. 2017

212 citations recorded by the source corpus.

Feature extraction becomes increasingly important as data grows high dimensional. Autoencoder as a neural network based feature extraction method achieves great success in generating abstract features of high dimensional data. However, it fails to consider the relationships of data samples which may affect experimental results of using original and new features. In this paper, we propose a Relation Autoencoder model considering both data features and their relationships. We also extend it to work with other major autoencoder models including Sparse Autoencoder, Denoising Autoencoder and Variational Autoencoder. The proposed relational autoencoder models are evaluated on a set of benchmark datasets and the experimental results show that considering data relationships can generate more robust features which achieve lower construction loss and then lower error rate in further classification compared to the other variants of autoencoders.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

In Signal Processing

Citations in the corpus

AutoML: A Survey of the State-of-the-Art (2019, methodology): “[82] propose a Relation Autoencoder model considering both data features and their relationships.”
Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019 (2019, background): “AEs’ hyperparameters are similar to DL hyperparameters.”
A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines (2018, background): “The relational AE [88] modiﬁes the objective function to take into account the ﬁdelity of the reconstruction of relationships among samples.”
Deep Learning for Financial Applications : A Survey (2020, background): “imensionsandfeatureextractioninAEcausesomedrawbacks. Focusing on minimizing the loss of the data relationship in the code ofAEcauses the loss of some signiﬁcantdatarelationship. ThismaybeadrawbackofAE[33]. Figure7showsthebasic AEstructure. (QFRGHU 'HFRGHU ,QSXW 2XWSXW &RGH Figure7: BasicAut”
Unsupervised Pre-training of a Deep LSTM-based Stacked Autoencoder for Multivariate Time Series Forecasting Problems (2019, unknown): “Meng et al . used it also in order to train the stacked denoising sparse autoencoder layer-by-layer 38 .”