Guardado en:
Detalles Bibliográficos
Autores principales: Bertrand, Jan Henrik, Hoffmann, David B., Gargano, Jacopo Pio, Mombaerts, Laurent, Taws, Jonathan
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2402.18164
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913677260619776
author Bertrand, Jan Henrik
Hoffmann, David B.
Gargano, Jacopo Pio
Mombaerts, Laurent
Taws, Jonathan
author_facet Bertrand, Jan Henrik
Hoffmann, David B.
Gargano, Jacopo Pio
Mombaerts, Laurent
Taws, Jonathan
contents Recent advances in representation learning have successfully leveraged the underlying domain-specific structure of data across various fields. However, representing diverse and complex entities stored in tabular format within a latent space remains challenging. In this paper, we introduce DEEPCAE, a novel method for calculating the regularization term for multi-layer contractive autoencoders (CAEs). Additionally, we formalize a general-purpose entity embedding framework and use it to empirically show that DEEPCAE outperforms all other tested autoencoder variants in both reconstruction performance and downstream prediction performance. Notably, when compared to a stacked CAE across 13 datasets, DEEPCAE achieves a 34% improvement in reconstruction error.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18164
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Autoencoder-based General Purpose Representation Learning for Customer Embedding
Bertrand, Jan Henrik
Hoffmann, David B.
Gargano, Jacopo Pio
Mombaerts, Laurent
Taws, Jonathan
Machine Learning
Artificial Intelligence
68T-02
Recent advances in representation learning have successfully leveraged the underlying domain-specific structure of data across various fields. However, representing diverse and complex entities stored in tabular format within a latent space remains challenging. In this paper, we introduce DEEPCAE, a novel method for calculating the regularization term for multi-layer contractive autoencoders (CAEs). Additionally, we formalize a general-purpose entity embedding framework and use it to empirically show that DEEPCAE outperforms all other tested autoencoder variants in both reconstruction performance and downstream prediction performance. Notably, when compared to a stacked CAE across 13 datasets, DEEPCAE achieves a 34% improvement in reconstruction error.
title Autoencoder-based General Purpose Representation Learning for Customer Embedding
topic Machine Learning
Artificial Intelligence
68T-02
url https://arxiv.org/abs/2402.18164