《Deep Learning based Recommender System: A Survey and New Perspectives》及相关文献

        最近读了2018年发表在ACM Computing Snrveys上的一篇关于基于深度学习的推荐系统的比较全面的综述《Deep Learning based Recommender System: A Survey and New Perspectives》，这篇综述简要介绍了多种常用的深度学习技术及其在推荐领域的应用，每种深度学习模型对应多篇参考文献，一共200多篇文献，从每种深度学习模型或框架对应的参考文献中挑出了几篇，如下：

1. 多层感知机/MLP

1. A multi-view deep learning approach for cross domain user modeling in recommendation systems
2. Learning deep structured semantic models for web search using clickthrough data
3. Neural Network Matrix Factorization
4. Wide & deep learning for recommender systems

2. 自编码器/AE

5. Autorec: Autoencoders meet collaborative filltering
6. AutoSVD++: An Efficient Hybrid Collaborative Filtering Model via Contractive Auto-encoders
7. Collaborative deep learning for recommender systems
8. Collaborative deep ranking: a hybrid pair-wise recommendation algorithm with implicit feedback
9. Collaborative denoising auto-encoders for top-n recommender systems
10. Deep collaborative €filtering via marginalized denoising auto-encoder
11. DLTSR: A Deep Learning Framework for Recommendation of Long-tail Web Services

3. 卷积神经网络/CNN

12. 3D Convolutional Networks for Session-based Recommendation with Content Features
13. Collaborative Deep Metric Learning for Video Understanding
14. ConTagNet: exploiting user context for image tag recommendation
15. Convolutional matrix factorization for document context-aware recommendation
16. Deep content-based music recommendation
17. Graph convolutional matrix completion
18. Graph Convolutional Neural Networks for Web-Scale Recommender Systems
19. Joint Deep Modeling of Users and Items Using Reviews for Recommendation
20. Outer Product-based Neural Collaborative Filtering
21. Personalized top-n sequential recommendation via convolutional sequence embedding
22. What Your Images Reveal: Exploiting Visual Contents for Point-of-Interest Recommendation

4. 循环神经网络/RNN

23. Contextual Sequence Modeling for Recommendation with Recurrent Neural Networks
24. Joint Deep Modeling of Users and Items Using Reviews for Recommendation
25. Multi-rate deep learning for temporal recommendation
26. Neural Rating Regression with Abstractive Tips Generation for Recommendation
27. Parallel recurrent neural network architectures for feature-rich session-based recommendation
28. Personal recommendation using deep recurrent neural networks in NetEase
29. Q&R: A Two-Stage Approach toward Interactive
30. Recurrent coevolutionary latent feature processes for continuous-time recommendation
31. Recurrent recommender networks
32. Session-based recommendations with recurrent neural networks

5. 受限玻尔兹曼机/RBM

33. A non-iid framework for collaborative filltering with restricted boltzmann machines
34. atrank: an attention-based user behavior modeling framework for recommend
35. Restricted Boltzmann machines for collaborative filtering

6. 神经自回归分布估计/NADE

36. A Neural Autoregressive Approach to Collaborative Filtering
37. Collaborative Filtering with User-Item Co-Autoregressive Models

7. 对抗网络/AN

38. Adversarial Personalized Ranking for Recommendation

8. 注意力模型/AM

39. Hashtag Recommendation for Multimodal Microblog Using Co-Attention Network
40. Hashtag recommendation using attention-based convolutional neural network
41. Hashtag recommendation with topical attention-based LSTM
42. Next Item Recommendation with Self-Attention
43. Sequential Recommender System based on Hierarchical Attention Networks

9. 深度强化学习/DRL

44. A Contextual-Bandit Approach to Personalized News Article Recommendation
45. DRN: A Deep Reinforcement Learning Framework for News Recommendation
46. IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models
47. Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning

10. CNN & Autoencoder

48. Collaborative Knowledge Base Embedding forRecommender Systems

11. CNN & Autoencoder

49. Hashtag Recommendation for Multimodal MicroblogUsing Co-Attention Network
50. Neural Citation Network for Context-Aware CitationRecommendation
51. Personalized Key Frame Recommendation
52. Quote Recommendation in Dialogueusing Deep Neural Network

12. RNN & Autoencoder

53. Collaborative Recurrent Autoencoder–Recommend while Learning to Fill in the Blanks

13. RNN with DRL

• Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation

欢迎交流！ QQ：3408649893