Utilizing Half Convolutional Autoencoder to Generate User and Item Vectors for Initialization in Matrix Factorization
Open Access
- 4 January 2022
- journal article
- research article
- Published by MDPI AG in Future Internet
- Vol. 14 (1) , 20
Abstract
Recommendation systems based on convolutional neural network (CNN) have attracted great attention due to their effectiveness in processing unstructured data such as images or audio. However, a huge amount of raw data produced by data crawling and digital transformation is structured, which makes it difficult to utilize the advantages of CNN. This paper introduces a novel autoencoder, named Half Convolutional Autoencoder, which adopts convolutional layers to discover the high-order correlation between structured features in the form of Tag Genome, the side information associated with each movie in the MovieLens 20 M dataset, in order to generate a robust feature vector. Subsequently, these new movie representations, along with the introduction of users’ characteristics generated via Tag Genome and their past transactions, are applied into well-known matrix factorization models to resolve the initialization problem and enhance the predicting results. This method not only outperforms traditional matrix factorization techniques by at least 5.35% in terms of accuracy but also stabilizes the training process and guarantees faster convergence.Keywords
Funding Information
- Hanoi University of Science and Technology (T2020-PC-024)
This publication has 34 references indexed in Scilit:
- Concept-based item representations for a cross-lingual content-based recommendation processInformation Sciences, 2016
- Collaborative Deep Learning for Recommender Systems2015
- AutoRec2015
- Scaling factorization machines to relational dataProceedings of the VLDB Endowment, 2013
- A hybrid content-based and item-based collaborative filtering approach to recommend TV programs enhanced with singular value decompositionInformation Sciences, 2010
- Content-based Recommender Systems: State of the Art and Trends2010
- Factor in the neighborsACM Transactions on Knowledge Discovery From Data, 2010
- SVD based initialization: A head start for nonnegative matrix factorizationPattern Recognition, 2008
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Improving non-negative matrix factorizations through structured initializationPattern Recognition, 2004