Self-Supervised Feature Specific Neural Matrix Completion

Self-Supervised Feature Specific Neural Matrix Completion

Unsupervised matrix completion algorithms mostly model the data generation process by using linear latent variable models. Recently proposed algorithms introduce non-linearity via multi-layer perceptrons (MLP), and self-supervision by setting separate linear regression frameworks for each feature to...

Full description

Bibliographic Details
Main Authors: Mehmet Aktukmak, Samuel M. Mercier, Ismail Uysal
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Matrix completion
non-linear regression
neural networks
self-supervised learning
Online Access:https://ieeexplore.ieee.org/document/9245478/

Internet

https://ieeexplore.ieee.org/document/9245478/

Similar Items