Regularizing autoencoder-based matrix completion models via manifold learning

Conference Paper

Autoencoders are popular among neural-network-based 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.

Full Text

Duke Authors

Cited Authors

  • Nguyen, DM; Tsiligianni, E; Calderbank, R; Deligiannis, N

Published Date

  • November 29, 2018

Published In

Volume / Issue

  • 2018-September /

Start / End Page

  • 1880 - 1884

International Standard Serial Number (ISSN)

  • 2219-5491

International Standard Book Number 13 (ISBN-13)

  • 9789082797015

Digital Object Identifier (DOI)

  • 10.23919/EUSIPCO.2018.8553528

Citation Source

  • Scopus