A Deep Learning Based Collaborative Neural Network Framework for Recommender System

Maram Almaghrabi, Girija Chetty

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

Deep learning based neural networks have been attracting significant interest lately, due to their success in complex automatic recognition tasks in many artificial intelligence areas such as language recognition ,computer vision and expert systems. However, in recommendation systems, they have not been exploited fully, and most of the systems rely on traditional collaborative filtering with matrix factorization approaches. In this paper we suggest a novel approach based on deep learning-based augmentation of the collaborative filtering approach for predicting user ratings for different types of media collections in online databases and libraries, including movies, music and book collections. Though there have been few approaches proposed based on deep learning for recommender systems, they were mainly used for modelling additional complementary information available in terms of images, text or acoustic information from different items in the collections. The main component, the interaction between the item and the user was still modelled with traditional matrix factorization approaches, which uses the dot product to extract the latent features between users and items. By augmenting the latent features extracted with deep learning based neural network models, it is possible to capture the hidden interactions and can lead to better recommender system performance even with sparse and unbalanced datasets. The experimental evaluation of the proposed approach based on four different publicly available datasets involving movies, music and book collections, show promising results, in terms of different performance metrics including accuracy and mean absolute error. Experiments on four datasets show the effectiveness of our proposed frameworks.

Original languageEnglish
Title of host publicationProceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018
EditorsDaniel Howard, Md Rezaul Bashar, Phill Kyu Rhee
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages128-135
Number of pages8
ISBN (Electronic)9781728104041
ISBN (Print)9781728104058
DOIs
Publication statusPublished - 15 Jan 2019
EventInternational Conference on Machine Learning and Data Engineering : iCMLDE 2018 - Western Sydney University, Sydney, Australia
Duration: 3 Dec 20187 Dec 2018
http://www.icmlde.net.au/Home.aspx

Publication series

NameProceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018

Conference

ConferenceInternational Conference on Machine Learning and Data Engineering
CountryAustralia
CitySydney
Period3/12/187/12/18
Internet address

Fingerprint

Recommender systems
Learning
Neural networks
Collaborative filtering
Artificial Intelligence
Motion Pictures
Music
Factorization
Expert Systems
Neural Networks (Computer)
Acoustics
Expert systems
Computer vision
Libraries
Artificial intelligence
Language
Databases
Deep learning
Datasets
Experiments

Cite this

Almaghrabi, M., & Chetty, G. (2019). A Deep Learning Based Collaborative Neural Network Framework for Recommender System. In D. Howard, M. R. Bashar, & P. K. Rhee (Eds.), Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018 (pp. 128-135). [8614014] (Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/icmlde.2018.00031
Almaghrabi, Maram ; Chetty, Girija. / A Deep Learning Based Collaborative Neural Network Framework for Recommender System. Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018. editor / Daniel Howard ; Md Rezaul Bashar ; Phill Kyu Rhee. IEEE, Institute of Electrical and Electronics Engineers, 2019. pp. 128-135 (Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018).
@inproceedings{689643cc45bc4584a7132a5f401c7187,
title = "A Deep Learning Based Collaborative Neural Network Framework for Recommender System",
abstract = "Deep learning based neural networks have been attracting significant interest lately, due to their success in complex automatic recognition tasks in many artificial intelligence areas such as language recognition ,computer vision and expert systems. However, in recommendation systems, they have not been exploited fully, and most of the systems rely on traditional collaborative filtering with matrix factorization approaches. In this paper we suggest a novel approach based on deep learning-based augmentation of the collaborative filtering approach for predicting user ratings for different types of media collections in online databases and libraries, including movies, music and book collections. Though there have been few approaches proposed based on deep learning for recommender systems, they were mainly used for modelling additional complementary information available in terms of images, text or acoustic information from different items in the collections. The main component, the interaction between the item and the user was still modelled with traditional matrix factorization approaches, which uses the dot product to extract the latent features between users and items. By augmenting the latent features extracted with deep learning based neural network models, it is possible to capture the hidden interactions and can lead to better recommender system performance even with sparse and unbalanced datasets. The experimental evaluation of the proposed approach based on four different publicly available datasets involving movies, music and book collections, show promising results, in terms of different performance metrics including accuracy and mean absolute error. Experiments on four datasets show the effectiveness of our proposed frameworks.",
keywords = "Collaborative Filtering, Deep learning, Neural Network, Recommender system",
author = "Maram Almaghrabi and Girija Chetty",
year = "2019",
month = "1",
day = "15",
doi = "10.1109/icmlde.2018.00031",
language = "English",
isbn = "9781728104058",
series = "Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
pages = "128--135",
editor = "Daniel Howard and Bashar, {Md Rezaul} and Rhee, {Phill Kyu}",
booktitle = "Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018",
address = "United States",

}

Almaghrabi, M & Chetty, G 2019, A Deep Learning Based Collaborative Neural Network Framework for Recommender System. in D Howard, MR Bashar & PK Rhee (eds), Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018., 8614014, Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018, IEEE, Institute of Electrical and Electronics Engineers, pp. 128-135, International Conference on Machine Learning and Data Engineering , Sydney, Australia, 3/12/18. https://doi.org/10.1109/icmlde.2018.00031

A Deep Learning Based Collaborative Neural Network Framework for Recommender System. / Almaghrabi, Maram; Chetty, Girija.

Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018. ed. / Daniel Howard; Md Rezaul Bashar; Phill Kyu Rhee. IEEE, Institute of Electrical and Electronics Engineers, 2019. p. 128-135 8614014 (Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - A Deep Learning Based Collaborative Neural Network Framework for Recommender System

AU - Almaghrabi, Maram

AU - Chetty, Girija

PY - 2019/1/15

Y1 - 2019/1/15

N2 - Deep learning based neural networks have been attracting significant interest lately, due to their success in complex automatic recognition tasks in many artificial intelligence areas such as language recognition ,computer vision and expert systems. However, in recommendation systems, they have not been exploited fully, and most of the systems rely on traditional collaborative filtering with matrix factorization approaches. In this paper we suggest a novel approach based on deep learning-based augmentation of the collaborative filtering approach for predicting user ratings for different types of media collections in online databases and libraries, including movies, music and book collections. Though there have been few approaches proposed based on deep learning for recommender systems, they were mainly used for modelling additional complementary information available in terms of images, text or acoustic information from different items in the collections. The main component, the interaction between the item and the user was still modelled with traditional matrix factorization approaches, which uses the dot product to extract the latent features between users and items. By augmenting the latent features extracted with deep learning based neural network models, it is possible to capture the hidden interactions and can lead to better recommender system performance even with sparse and unbalanced datasets. The experimental evaluation of the proposed approach based on four different publicly available datasets involving movies, music and book collections, show promising results, in terms of different performance metrics including accuracy and mean absolute error. Experiments on four datasets show the effectiveness of our proposed frameworks.

AB - Deep learning based neural networks have been attracting significant interest lately, due to their success in complex automatic recognition tasks in many artificial intelligence areas such as language recognition ,computer vision and expert systems. However, in recommendation systems, they have not been exploited fully, and most of the systems rely on traditional collaborative filtering with matrix factorization approaches. In this paper we suggest a novel approach based on deep learning-based augmentation of the collaborative filtering approach for predicting user ratings for different types of media collections in online databases and libraries, including movies, music and book collections. Though there have been few approaches proposed based on deep learning for recommender systems, they were mainly used for modelling additional complementary information available in terms of images, text or acoustic information from different items in the collections. The main component, the interaction between the item and the user was still modelled with traditional matrix factorization approaches, which uses the dot product to extract the latent features between users and items. By augmenting the latent features extracted with deep learning based neural network models, it is possible to capture the hidden interactions and can lead to better recommender system performance even with sparse and unbalanced datasets. The experimental evaluation of the proposed approach based on four different publicly available datasets involving movies, music and book collections, show promising results, in terms of different performance metrics including accuracy and mean absolute error. Experiments on four datasets show the effectiveness of our proposed frameworks.

KW - Collaborative Filtering

KW - Deep learning

KW - Neural Network

KW - Recommender system

UR - http://www.scopus.com/inward/record.url?scp=85062226772&partnerID=8YFLogxK

U2 - 10.1109/icmlde.2018.00031

DO - 10.1109/icmlde.2018.00031

M3 - Conference contribution

SN - 9781728104058

T3 - Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018

SP - 128

EP - 135

BT - Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018

A2 - Howard, Daniel

A2 - Bashar, Md Rezaul

A2 - Rhee, Phill Kyu

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Almaghrabi M, Chetty G. A Deep Learning Based Collaborative Neural Network Framework for Recommender System. In Howard D, Bashar MR, Rhee PK, editors, Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018. IEEE, Institute of Electrical and Electronics Engineers. 2019. p. 128-135. 8614014. (Proceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018). https://doi.org/10.1109/icmlde.2018.00031