Neural Embedding Singular Value Decomposition for Collaborative Filtering
- 29 April 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 33 (10) , 6021-6029
Abstract
Singular value decomposition (SVD) is one of the most effective algorithms in recommender systems (RSs). Due to the iterative nature of SVD algorithms, one big challenge is initialization that has a major impact on the convergence and performance of RSs. Unfortunately, existing SVD algorithms in the literature typically initialize the user and item features in a random manner; thus, data information is not fully utilized. This work addresses the challenge of developing an efficient initialization method for SVD algorithms. We propose a general neural embedding initialization framework, where a low-complexity probabilistic autoencoder neural network initializes the features of user and item. This framework supports explicit and implicit feedback data sets. The design details of our proposed framework are elaborated and discussed. Experimental results show that RSs based on our proposed initialization framework outperform the state-of-the-art methods in rating prediction. Moreover, regarding item ranking, our proposed framework shows an improvement of at least 2.20% ~5.74% than existing SVD algorithms and other matrix factorization methods in the literature.Keywords
Funding Information
- National Natural Science Foundation of China (61672439)
- Fundamental Research Funds for the Central Universities (20720181004)
This publication has 24 references indexed in Scilit:
- Collaborative Denoising Auto-Encoders for Top-N Recommender Systems2016
- New SVD based initialization strategy for non-negative matrix factorizationPattern Recognition Letters, 2015
- AutoRec2015
- FISM2013
- Enhancing matrix factorization through initialization for implicit feedback databases2012
- Introduction to Recommender Systems Handbook2010
- Factorization meets the neighborhood2008
- SVD based initialization: A head start for nonnegative matrix factorizationPattern Recognition, 2008
- Projected Gradient Methods for Nonnegative Matrix FactorizationNeural Computation, 2007
- Item-based collaborative filtering recommendation algorithms2001