Fast Dual-Regularized Autoencoder for Sparse Biological Data. (arXiv:2401.16664v1 [cs.LG])

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.

accuracy algorithms applications arxiv autoencoder cs.lg data discovery drug discovery inference linear linear model matrix product product recommendation recommendation recommender systems relationship speed systems