Fast Dual-Regularized Autoencoder for Sparse Biological Data

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Poleksic, Aleksandar
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909135351578624
author Poleksic, Aleksandar
author_facet Poleksic, Aleksandar
contents Relationship inference from sparse data is an important task with applications ranging from product recommendation to drug discovery. A recently proposed linear model for sparse matrix completion has demonstrated surprising advantage in speed and accuracy over more sophisticated recommender systems algorithms. Here we extend the linear model to develop a shallow autoencoder for the dual neighborhood-regularized matrix completion problem. We demonstrate the speed and accuracy advantage of our approach over the existing state-of-the-art in predicting drug-target interactions and drug-disease associations.
format Preprint
id arxiv_https___arxiv_org_abs_2401_16664
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fast Dual-Regularized Autoencoder for Sparse Biological Data
Poleksic, Aleksandar
Machine Learning
92C42
J.3
Relationship inference from sparse data is an important task with applications ranging from product recommendation to drug discovery. A recently proposed linear model for sparse matrix completion has demonstrated surprising advantage in speed and accuracy over more sophisticated recommender systems algorithms. Here we extend the linear model to develop a shallow autoencoder for the dual neighborhood-regularized matrix completion problem. We demonstrate the speed and accuracy advantage of our approach over the existing state-of-the-art in predicting drug-target interactions and drug-disease associations.
title Fast Dual-Regularized Autoencoder for Sparse Biological Data
topic Machine Learning
92C42
J.3
url https://arxiv.org/abs/2401.16664