Papers by Houssem Eddine Zerrad
2021 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), 2021
Recommender systems that provide recommendations based uniquely on information over users and ite... more Recommender systems that provide recommendations based uniquely on information over users and items may not be very accurate in some situations. Therefore, adding contextual information to recommendations may be a good choice resulting in a system with increased precision. In an early work, we proposed an Ensemble Variational Autoencoders (EnsVAE) framework for recommendation. EnsVAE is adjusted to output interest probabilities by learning the distribution of each item's ratings and attempts to provide diverse novel items that are pertinent to users. In this paper, we propose and investigate a context awareness framework based on the Ensemblist Variational Autoencoders model with integrating the contextual information. The context awareness EnsVAE can easily be inferred from preceding sub-recommenders or applied as a filter to the final output. Test performed on real dataset, using an instance of the proposed framework show clear improvement compared to baseline architectures wi...
IEEE Access
Recommender systems are information software that retrieves relevant items for users from massive... more Recommender systems are information software that retrieves relevant items for users from massive sources of data. The variational autoencoder (VAE) has proven to be a promising approach for recommendation systems, as it can explore high-level user-item relations and extract contingencies from the input effectively. However, the previous variants of VAE have so far seen limited application to domain-specific recommendations that require additional side information. Hence, The Ensemble Variational Autoencoder framework for recommendations (EnsVAE) is proposed. This architecture specifies a procedure to transform sub-recommenders' predicted utility matrix into interest probabilities that allow the VAE to represent the variation in their aggregation. To evaluate the performance of EnsVAE, an instancecalled the ''Ensemblist GRU/GLOVE model''-is developed. It is based on two innovative recommender systems: 1-) a new ''GloVe content-based filtering recommender'' (GloVe-CBF) that exploits the strengths of embedding-based representations and stacking ensemble learning techniques to extract features from the item-based side information. 2-) a variant of neural collaborative filtering recommender, named ''Gate Recurrent Unit-based Matrix Factorization recommender'' (GRU-MF). It models a high level of non-linearities and exhibits interactions between users and items in latent embeddings, reducing user biases towards items that are rated frequently by users. The developed instance speeds up the reconstruction of the utility matrix with increased accuracy. Additionally, it can switch between one of its sub-recommenders according to the context of their use. Our findings reveal that EnsVAE instances retain as much information as possible during the reconstruction of the utility matrix. Furthermore, the trained VAE's generative trait tackles the cold-start problem by accurately estimating the interest probabilities of newly-introduced users and resources. The empirical study on real-world datasets proves that EnsVAE significantly outperforms the state-of-the-art methods in terms of recommendation performances. INDEX TERMS Hybrid recommender systems, neural recommender models, collaborative filtering, content-based filtering, variational autoencoders.
Uploads
Papers by Houssem Eddine Zerrad