Deep Variational Embedding Representation on Neural Collaborative Filtering Recommender Systems
Open Access
- 20 April 2022
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 12 (9) , 4168
Abstract
Visual representation of user and item relations is an important issue in recommender systems. This is a big data task that helps to understand the underlying structure of the information, and it can be used by company managers and technical staff. Current collaborative filtering machine learning models are designed to improve prediction accuracy, not to provide suitable visual representations of data. This paper proposes a deep learning model specifically designed to display the existing relations among users, items, and both users and items. Making use of representative datasets, we show that by setting small embedding sizes of users and items, the recommender system accuracy remains nearly unchanged; it opens the door to the use of bidimensional and three-dimensional representations of users and items. The proposed neural model incorporates variational embedding stages to “unpack” (extend) embedding representations, which facilitates identifying individual samples. It also replaces the join layers in current models with a Lambda Euclidean layer that better catches the space representation of samples. The results show numerical and visual improvements when the proposed model is used compared to the baselines. The proposed model can be used to explain recommendations and to represent demographic features (gender, age, etc.) of samples.Keywords
This publication has 37 references indexed in Scilit:
- Method to interactively visualize and navigate related informationExpert Systems with Applications, 2018
- Deep Matrix Factorization Models for Recommender Systems2017
- Collaborative User Network Embedding for Social Recommender Systems2017
- Neural Collaborative Filtering2017
- Learning Distributed Representations for Recommender Systems with a Network Embedding Approach2016
- Wide & Deep Learning for Recommender Systems2016
- Collaborative Knowledge Base Embedding for Recommender Systems2016
- A non negative matrix factorization for collaborative filtering recommender systems based on a Bayesian probabilistic modelKnowledge-Based Systems, 2016
- The MovieLens DatasetsACM Transactions on Interactive Intelligent Systems, 2015
- Hierarchical graph maps for visualization of collaborative recommender systemsJournal of Information Science, 2013