Enhancing Collaborative Variational Autoencoder with Tag and Citation Information for Scientific Article Recommendation

Hybrid methods such as collaborative deep learning (CDL) and collaborative variational autoencoder (CVAE) have become state-ofthe-art methods in recommender systems for scientific articles. However, they typically use only information from titles and abstracts of articles, and ignore potentially useful information in the tags and citations. Therefore, they may miss articles that contain vastly different content from other articles, although those articles present the same topic. We addressed this problem by developing the CiT-CVAE model that considers tag and citation information when providing recommendations. Our experimental results indicate that the proposed model achieves consistent improvement compared with CDL and CVAE.

[1]  James She,et al.  Collaborative Variational Autoencoder for Recommender Systems , 2017, KDD.

[2]  Zhaohui Wu,et al.  On Deep Learning for Trust-Aware Recommendations in Social Networks , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[3]  Dit-Yan Yeung,et al.  Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks , 2016, NIPS.

[4]  Martin Ester,et al.  Collaborative Denoising Auto-Encoders for Top-N Recommender Systems , 2016, WSDM.

[5]  Sheng Li,et al.  Deep Collaborative Filtering via Marginalized Denoising Auto-encoder , 2015, CIKM.

[6]  Tinghuai Ma,et al.  Social Network and Tag Sources Based Augmenting Collaborative Recommender System , 2015, IEICE Trans. Inf. Syst..

[7]  Dit-Yan Yeung,et al.  Relational Stacked Denoising Autoencoder for Tag Recommendation , 2015, AAAI.

[8]  Dit-Yan Yeung,et al.  Collaborative Deep Learning for Recommender Systems , 2014, KDD.

[9]  Min-Yen Kan,et al.  A comprehensive evaluation of scholarly paper recommendation using potential citation papers , 2014, International Journal on Digital Libraries.

[10]  Yizhou Sun,et al.  Meta-Path-Based Ranking with Pseudo Relevance Feedback on Heterogeneous Graph for Citation Recommendation , 2014, CIKM.

[11]  Jiawei Han,et al.  ClusCite: effective citation recommendation by information network-based clustering , 2014, KDD.

[12]  Hyoung-Joo Kim,et al.  A framework for tag-aware recommender systems , 2014, Expert Syst. Appl..

[13]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[14]  Wu-Jun Li,et al.  Collaborative Topic Regression with Social Regularization for Tag Recommendation , 2013, IJCAI.

[15]  Min-Yen Kan,et al.  Exploiting potential citation papers in scholarly paper recommendation , 2013, JCDL '13.

[16]  J. Bobadilla,et al.  Recommender systems survey , 2013, Knowl. Based Syst..

[17]  Yi-Cheng Zhang,et al.  Tag-Aware Recommender Systems: A State-of-the-Art Survey , 2011, Journal of Computer Science and Technology.

[18]  Chong Wang,et al.  Collaborative topic modeling for recommending scientific articles , 2011, KDD.

[19]  Qiudan Li,et al.  A recommender system based on tag and time information for social tagging systems , 2011, Expert Syst. Appl..

[20]  Min-Yen Kan,et al.  Scholarly paper recommendation via user's recent research interests , 2010, JCDL '10.

[21]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[22]  Deepak Agarwal,et al.  Regression-based latent factor models , 2009, KDD.

[23]  Lars Schmidt-Thieme,et al.  BPR: Bayesian Personalized Ranking from Implicit Feedback , 2009, UAI.

[24]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[25]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[26]  Ken Lang,et al.  NewsWeeder: Learning to Filter Netnews , 1995, ICML.