PHD: A Probabilistic Model of Hybrid Deep Collaborative Filtering for Recommender Systems

Jie Liu, Dong Wang, Yue Ding
Proceedings of the Ninth Asian Conference on Machine Learning, PMLR 77:224-239, 2017.

Abstract

Collaborative Filtering (CF), a well-known approach in producing recommender systems, has achieved wide use and excellent performance not only in research but also in industry. However, problems related to cold start and data sparsity have caused CF to attract an increasing amount of attention in efforts to solve these problems. Traditional approaches adopt side information to extract effective latent factors but still have some room for growth. Due to the strong characteristic of feature extraction in deep learning, many researchers have employed it with CF to extract effective representations and to enhance its performance in rating prediction. Based on this previous work, we propose a probabilistic model that combines a stacked denoising autoencoder and a convolutional neural network together with auxiliary side information (i.e, both from users and items) to extract users and items’ latent factors, respectively. Extensive experiments for four datasets demonstrate that our proposed model outperforms other traditional approaches and deep learning models making it state of the art.

Cite this Paper

BibTeX
@InProceedings{pmlr-v77-liu17a, title = {PHD: A Probabilistic Model of Hybrid Deep Collaborative Filtering for Recommender Systems}, author = {Liu, Jie and Wang, Dong and Ding, Yue}, booktitle = {Proceedings of the Ninth Asian Conference on Machine Learning}, pages = {224--239}, year = {2017}, editor = {Zhang, Min-Ling and Noh, Yung-Kyun}, volume = {77}, series = {Proceedings of Machine Learning Research}, address = {Yonsei University, Seoul, Republic of Korea}, month = {15--17 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v77/liu17a/liu17a.pdf}, url = {https://proceedings.mlr.press/v77/liu17a.html}, abstract = {Collaborative Filtering (CF), a well-known approach in producing recommender systems, has achieved wide use and excellent performance not only in research but also in industry. However, problems related to cold start and data sparsity have caused CF to attract an increasing amount of attention in efforts to solve these problems. Traditional approaches adopt side information to extract effective latent factors but still have some room for growth. Due to the strong characteristic of feature extraction in deep learning, many researchers have employed it with CF to extract effective representations and to enhance its performance in rating prediction. Based on this previous work, we propose a probabilistic model that combines a stacked denoising autoencoder and a convolutional neural network together with auxiliary side information (i.e, both from users and items) to extract users and items’ latent factors, respectively. Extensive experiments for four datasets demonstrate that our proposed model outperforms other traditional approaches and deep learning models making it state of the art.} }
Endnote
%0 Conference Paper %T PHD: A Probabilistic Model of Hybrid Deep Collaborative Filtering for Recommender Systems %A Jie Liu %A Dong Wang %A Yue Ding %B Proceedings of the Ninth Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Min-Ling Zhang %E Yung-Kyun Noh %F pmlr-v77-liu17a %I PMLR %P 224--239 %U https://proceedings.mlr.press/v77/liu17a.html %V 77 %X Collaborative Filtering (CF), a well-known approach in producing recommender systems, has achieved wide use and excellent performance not only in research but also in industry. However, problems related to cold start and data sparsity have caused CF to attract an increasing amount of attention in efforts to solve these problems. Traditional approaches adopt side information to extract effective latent factors but still have some room for growth. Due to the strong characteristic of feature extraction in deep learning, many researchers have employed it with CF to extract effective representations and to enhance its performance in rating prediction. Based on this previous work, we propose a probabilistic model that combines a stacked denoising autoencoder and a convolutional neural network together with auxiliary side information (i.e, both from users and items) to extract users and items’ latent factors, respectively. Extensive experiments for four datasets demonstrate that our proposed model outperforms other traditional approaches and deep learning models making it state of the art.
APA
Liu, J., Wang, D. & Ding, Y.. (2017). PHD: A Probabilistic Model of Hybrid Deep Collaborative Filtering for Recommender Systems. Proceedings of the Ninth Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 77:224-239 Available from https://proceedings.mlr.press/v77/liu17a.html.

Related Material