Extendable Neural Matrix Completion
This addresses the limitation of existing neural-network-based matrix completion models in handling new samples, which is important for applications like recommender systems.
The paper tackles the problem of matrix completion by proposing a deep two-branch neural network model that can extend to samples not seen during training without retraining, achieving state-of-the-art performance in accuracy and extendability on movie rating datasets.
Matrix completion is one of the key problems in signal processing and machine learning, with applications ranging from image pro- cessing and data gathering to classification and recommender sys- tems. Recently, deep neural networks have been proposed as la- tent factor models for matrix completion and have achieved state- of-the-art performance. Nevertheless, a major problem with existing neural-network-based models is their limited capabilities to extend to samples unavailable at the training stage. In this paper, we propose a deep two-branch neural network model for matrix completion. The proposed model not only inherits the predictive power of neural net- works, but is also capable of extending to partially observed samples outside the training set, without the need of retraining or fine-tuning. Experimental studies on popular movie rating datasets prove the ef- fectiveness of our model compared to the state of the art, in terms of both accuracy and extendability.