< Terug naar vorige pagina

Publicatie

Regularizing autoencoder-based matrix completion models via manifold learning

Boekbijdrage - Boekhoofdstuk Conferentiebijdrage

Autoencoders are popular among neural-networkbased
matrix completion models due to their ability to retrieve
potential latent factors from the partially observed matrices.
Nevertheless, when training data is scarce their performance is
significantly degraded due to overfitting. In this paper, we mitigate
overfitting with a data-dependent regularization technique
that relies on the principles of multi-task learning. Specifically,
we propose an autoencoder-based matrix completion model that
performs prediction of the unknown matrix values as a main
task, and manifold learning as an auxiliary task. The latter acts
as an inductive bias, leading to solutions that generalize better.
The proposed model outperforms the existing autoencoder-based
models designed for matrix completion, achieving high reconstruction
accuracy in well-known datasets.
Boek: 2018 26th European Signal Processing Conference, EUSIPCO 2018
Volume: 2018-September
Pagina's: 1880-1884
Aantal pagina's: 5
Jaar van publicatie:2018
Trefwoorden:Autoencoder, Deep neural network, Matrix completion, Multi-task learning, Regularization
Auteurs:International
Toegankelijkheid:Open