Skip to main content

Geometric Matrix Completion With Deep Conditional Random Fields.

Publication ,  Journal Article
Nguyen, DM; Calderbank, R; Deligiannis, N
Published in: IEEE transactions on neural networks and learning systems
September 2020

The problem of completing high-dimensional matrices from a limited set of observations arises in many big data applications, especially recommender systems. The existing matrix completion models generally follow either a memory- or a model-based approach, whereas geometric matrix completion (GMC) models combine the best from both approaches. Existing deep-learning-based geometric models yield good performance, but, in order to operate, they require a fixed structure graph capturing the relationships among the users and items. This graph is typically constructed by evaluating a pre-defined similarity metric on the available observations or by using side information, e.g., user profiles. In contrast, Markov-random-fields-based models do not require a fixed structure graph but rely on handcrafted features to make predictions. When no side information is available and the number of available observations becomes very low, existing solutions are pushed to their limits. In this article, we propose a GMC approach that addresses these challenges. We consider matrix completion as a structured prediction problem in a conditional random field (CRF), which is characterized by a maximum a posteriori (MAP) inference, and we propose a deep model that predicts the missing entries by solving the MAP inference problem. The proposed model simultaneously learns the similarities among matrix entries, computes the CRF potentials, and solves the inference problem. Its training is performed in an end-to-end manner, with a method to supervise the learning of entry similarities. Comprehensive experiments demonstrate the superior performance of the proposed model compared to various state-of-the-art models on popular benchmark data sets and underline its superior capacity to deal with highly incomplete matrices.

Duke Scholars

Published In

IEEE transactions on neural networks and learning systems

DOI

EISSN

2162-2388

ISSN

2162-237X

Publication Date

September 2020

Volume

31

Issue

9

Start / End Page

3579 / 3593

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4602 Artificial intelligence
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Nguyen, D. M., Calderbank, R., & Deligiannis, N. (2020). Geometric Matrix Completion With Deep Conditional Random Fields. IEEE Transactions on Neural Networks and Learning Systems, 31(9), 3579–3593. https://doi.org/10.1109/tnnls.2019.2945111
Nguyen, Duc Minh, Robert Calderbank, and Nikos Deligiannis. “Geometric Matrix Completion With Deep Conditional Random Fields.IEEE Transactions on Neural Networks and Learning Systems 31, no. 9 (September 2020): 3579–93. https://doi.org/10.1109/tnnls.2019.2945111.
Nguyen DM, Calderbank R, Deligiannis N. Geometric Matrix Completion With Deep Conditional Random Fields. IEEE transactions on neural networks and learning systems. 2020 Sep;31(9):3579–93.
Nguyen, Duc Minh, et al. “Geometric Matrix Completion With Deep Conditional Random Fields.IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 9, Sept. 2020, pp. 3579–93. Epmc, doi:10.1109/tnnls.2019.2945111.
Nguyen DM, Calderbank R, Deligiannis N. Geometric Matrix Completion With Deep Conditional Random Fields. IEEE transactions on neural networks and learning systems. 2020 Sep;31(9):3579–3593.

Published In

IEEE transactions on neural networks and learning systems

DOI

EISSN

2162-2388

ISSN

2162-237X

Publication Date

September 2020

Volume

31

Issue

9

Start / End Page

3579 / 3593

Related Subject Headings

  • Artificial Intelligence & Image Processing
  • 4602 Artificial intelligence