deep-learning-for-recommender-systems

Deep Learning for Recommender Systems

1. Autoencoder model

// Solely on Deep learning:

• Autorec: Autoencoders meet collaborative filtering. https://dl.acm.org/citation.cfm?id=2742726, WWW 2015.
• Collaborative Denoising Auto-Encoders for Top-N Recommender Systems. https://dl.acm.org/citation.cfm?id=2835837, WSDM 2016.

// Integrate Deep Learning with Traditional Recommender System:

• Deep collaborative filtering via marginalized denoising auto-encoder. https://dl.acm.org/citation.cfm?id=2806527&CFID=995519407&CFTOKEN=19890743, CIKM 2015.
• Collaborative deep learning for recommender systems. https://arxiv.org/abs/1409.2944, KDD 2015.
• Collaborative Variational Autoencoder for Recommender Systems. https://dl.acm.org/citation.cfm?id=3098077, SIGKDD 2017.
• A Hybrid Collaborative Filtering Model with Deep Structure for Recommender Systems https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14676, AAAI 2017.
• AutoSVD++: An Efficient Hybrid Collaborative Filtering Model via Contractive Autoencoders. https://arxiv.org/abs/1704.00551, SIGIR 2017.

2. Recurrent Neural Network (RNN) model

// Solely on Deep learning:

• Parallel recurrent neural network architectures for feature-rich session-based recommendations. https://dl.acm.org/citation.cfm?id=2959167, RecSys 2016.
• Ask the gru: Multi-task learning for deep text recommendations. https://dl.acm.org/citation.cfm?id=2959180, RecSys 2016.
• Personal recommendation using deep recurrent neural networks in NetEase. http://dblp2.uni-trier.de/rec/html/conf/icde/WuRYCZZ16, ICDE 2016.
• A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. https://dl.acm.org/citation.cfm?id=3079684, UMAP 2017.
• Recurrent recommender networks. https://dl.acm.org/citation.cfm?id=3018689, WSDM 2017.

// Integrate Deep Learning with Traditional Recommender System:

• Modelling Contextual Information in Session-Aware Recommender Systems with Neural Networks. https://dl.acm.org/citation.cfm?id=2959162, RecSys 2016.
• Embedding-based News Recommendation for Millions of Users. https://dl.acm.org/citation.cfm?id=3098108, KDD 2017.

3. Convolutional Neural Network (CNN) model

// Solely on Deep learning:

• Hashtag Recommendation Using Attention-Based Convolutional Neural Network. https://dl.acm.org/citation.cfm?id=3061010, IJCAI 2016.
• Personalized Deep Learning for Tag Recommendation. https://link.springer.com/chapter/10.1007/978-3-319-57454-7_15, PAKDD 2017.
• Dynamic Attention Deep Model for Article Recommendation by Learning Human Editorsfi Demonstration. http://www.kdd.org/kdd2017/papers/view/dynamic-attention-deep-model-for-article-recommendation-by-learning-human-e, KDD 2017.

// Integrate Deep Learning with Traditional Recommender System:

• Deep content-based music recommendation. https://dl.acm.org/citation.cfm?id=2999907, NIPS 2013.
• Convolutional matrix factorization for document context-aware recommendation. https://dl.acm.org/citation.cfm?id=2959165, RecSys 2016.
• VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback. https://arxiv.org/abs/1510.01784, AAAI 2016.
• Joint Deep Modeling of Users and Items Using Reviews for Recommendation. https://dl.acm.org/citation.cfm?id=3018665, WSDM 2017.
• DeepStyle: Learning User Preferences for Visual Recommendation. https://dl.acm.org/citation.cfm?id=3080658, SIGIR 2017.

4. Deep composite models

// CNN and Autoencoder

• Collaborative knowledge base embedding for recommender systems. https://dl.acm.org/citation.cfm?id=2939673, KDD 2016.

5. Attention model

• Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention. https://dl.acm.org/citation.cfm?id=3080797, SIGIR 2017.