# Regularizing Autoencoder-Based Matrix Completion Models via Manifold Learning

arXiv: https://arxiv.org/abs/1807.01798 · HTML: https://mlsanity.com/paper/1807.01798/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2018.

## Built on by (most cited first, 3 of 3)

- [Deep Nonlinear Hyperspectral Unmixing Using Multi-task Learning](https://mlsanity.com/paper/2402.03398/) (2024)
- [Matrix Completion via Nonsmooth Regularization of Fully Connected Neural Networks](https://mlsanity.com/paper/2403.10232/) (2024)
- [Rank-Constrained Deep Matrix Completion for Group Recommendation](https://mlsanity.com/paper/2606.01948/) (2026)

## Abstract (arXiv)

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.