Regularizing Autoencoder-Based Matrix Completion Models via Manifold Learning

TL;DR

This paper introduces a regularization method for autoencoder-based matrix completion that uses manifold learning as an auxiliary task to improve generalization, especially with limited data.

Contribution

It proposes a novel multi-task learning approach combining matrix prediction and manifold learning to enhance autoencoder performance in matrix completion tasks.

Findings

Outperforms existing autoencoder models in accuracy

Reduces overfitting with data-dependent regularization

Achieves high reconstruction accuracy on benchmark datasets

Abstract

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 mit- igate 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.