Discrete Collaborative Filtering

By Hanwang Zhang, Fumin Shen, Wei David Liu, Xiangnan He, Huanbo Luan, Tat-seng Chua. 2016

278 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Xiangnan He
2. Tat-seng Chua
3. Xiang Wang
4. Meng Wang
5. Hanwang Zhang
6. Liqiang Nie
7. Fei Wu
8. Jiawei Chen

In Computer Vision and Pattern Recognition

1. Xiangnan He
2. Tat-seng Chua
3. Xiang Wang
4. Dacheng Tao
5. Hanwang Zhang
6. Liqiang Nie
7. Meng Wang
8. Jingkuan Song

In Information Systems

1. Xiangnan He
2. Tat-seng Chua
3. Xiang Wang
4. Liqiang Nie
5. Fuli Feng
6. Meng Wang
7. Hanwang Zhang
8. Yongfeng Zhang

Citations in the corpus

• Neural Collaborative Filtering (2017, background): “As a natural extension of abundant work on explicit feedback [21, 46], methods on pointwise learning usually follow a regression framework by minimizing the squared loss between ŷui and its target value yui.”
• Adversarial Personalized Ranking for Recommendation (2018, background): “MF has been recognized as the basic yet most effective model in recommendation since several years [2, 20, 40].”
• Attributed Social Network Embedding (2017, methodology): “Lastly, we will consider improving the efficiency of SNE by learning to hash techniques [53] to make it suitable for large-scale industrial use.”
• NAIS: Neural Attentive Item Similarity Model for Recommendation (2018, background): “Popularized by theNetflix Prize,matrix factorization (MF)methods have become the most popular recommendation approach in academia and been widely studied in literatures [6], [7].”
• A Survey on Learning to Hash (2016, background): “This topic is attracting a lot of research efforts nowadays, such as collaborative hashing [89], [167], collaborative quantization [173], and cross-media hashing [134], [135], [178], [161], [83].”
• Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention (2017, methodology): “Since ACF is a generic attention-based CF framework, we plan to extend ACF in various CF models such as factorization machines [29], and the recently proposed Neural CF [20] and Discrete CF [43].”
• Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews (2018, methodology): “, matrix factorization [9, 21, 37]) are the most widely used and successful techniques for rating prediction, as demonstrated by the Netflix Prize contest [3].”
• Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization (2018, background): “Owing to the desiring property, hashing can be potentially applied to various applications, such as visual recognition [21], [36], [42], [43], machine learning [32], [33], [55], recommendation systems [56].”
• Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences (2019, background): “In the early stage of item recommendation, researchers focus on recommending similar users or items to a target user using history interactions alone, such as collaborative filtering (CF) [35], factorization machines [33], matrix factorization techniques [19], BPRMF [34], and their extensions [46].”
• Unifying Virtual and Physical Worlds (2017, background): “In the offline part, EBSNs also support and record user interactions in the physical world, where users can create and invite others to join social events, such as dining out and jogging, at specific places and times [Zhang et al. 2016].”
• Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks (2017, methodology): “As AFM has a relatively high complexity quadratic to the number of non-zero features, we will consider improving its learning efficiency, for example by using learning to hash [Zhang et al., 2016b; Shen et al., 2015] and data sampling [Wang et al.”
• Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System (2018, background): “Discrete hashing techniques [39, 40, 42] and binary coding of model parameters are suggested to speed up the calculation of the relevance score for a given ( q , d ) pair.”
• Neural Factorization Machines for Sparse Predictive Analytics (2017, methodology): “In future, we will improve the efficiency of NFM by resorting to hashing techniques [32, 41] to make it more suitable for large-scale applications and study its performance for other IR tasks, such as search ranking and targeted advertising.”
• Fast Matrix Factorization for Online Recommendation with Implicit Feedback (2016, methodology): “Among its various methods, matrix factorization (MF) is the most popular and effective technique that characterizes users and items by vectors of latent factors [15, 32].”
• Bias and Debias in Recommender System: A Survey and Future Directions (2020, background): “Another example is the discrete ranking model [44], [45], [46] which embeds user and items as binary codes to improve the efficiency of recommendation, which is at the expense of sacrificing the representation ability.”