Compositional Coding for Collaborative Filtering

Efficiency is crucial to the online recommender systems, especially for the ones which needs to deal with tens of millions of users and items. Because representing users and items as binary vectors for Collaborative Filtering (CF) can achieve fast user-item affinity computation in the Hamming space, in recent years, we have witnessed an emerging research effort in exploiting binary hashing techniques for CF methods. However, CF with binary codes naturally suffers from low accuracy due to limited representation capability in each bit, which impedes it from modeling complex structure of the data. In this work, we attempt to improve the efficiency without hurting the model performance by utilizing both the accuracy of real-valued vectors and the efficiency of binary codes to represent users/items. In particular, we propose the Compositional Coding for Collaborative Filtering (CCCF) framework, which not only gains better recommendation efficiency than the state-of-the-art binarized CF approaches but also achieves even higher accuracy than the real-valued CF method. Specifically, CCCF innovatively represents each user/item with a set of binary vectors, which are associated with a sparse real-value weight vector. Each value of the weight vector encodes the importance of the corresponding binary vector to the user/item. The continuous weight vectors greatly enhances the representation capability of binary codes, and its sparsity guarantees the processing speed. Furthermore, an integer weight approximation scheme is proposed to further accelerate the speed. Based on the CCCF framework, we design an efficient discrete optimization algorithm to learn its parameters. Extensive experiments on three real-world datasets show that our method outperforms the state-of-the-art binarized CF methods (even achieves better performance than the real-valued CF method) by a large margin in terms of both recommendation accuracy and efficiency. We publish our project at https://github.com/3140102441/CCCF.

[1]  Samy Bengio,et al.  Local collaborative ranking , 2014, WWW.

[2]  Abhinandan Das,et al.  Google news personalization: scalable online collaborative filtering , 2007, WWW '07.

[3]  Luo Si,et al.  Preference preserving hashing for efficient recommendation , 2014, SIGIR.

[4]  Hideki Nakayama,et al.  Compressing Word Embeddings via Deep Compositional Code Learning , 2017, ICLR.

[5]  Wei Liu,et al.  Discrete Graph Hashing , 2014, NIPS.

[6]  Xing Xie,et al.  Discrete Content-aware Matrix Factorization , 2017, KDD.

[7]  Mohan S. Kankanhalli,et al.  Exploiting Music Play Sequence for Music Recommendation , 2017, IJCAI.

[8]  James T. Kwok,et al.  Collaborative Filtering with Social Local Models , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[9]  Yiqun Liu,et al.  Improve collaborative filtering through bordered block diagonal form matrices , 2013, SIGIR.

[10]  Zhaochun Ren,et al.  Neural Attentive Session-based Recommendation , 2017, CIKM.

[11]  Wei Liu,et al.  Supervised Discrete Hashing , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Steven C. H. Hoi,et al.  Online Adaptive Passive-Aggressive Methods for Non-Negative Matrix Factorization and Its Applications , 2016, CIKM.

[13]  Xin Wang,et al.  Discrete Social Recommendation , 2019, AAAI.

[14]  Heng Tao Shen,et al.  Classification by Retrieval : Binarizing Data and Classifier , 2017 .

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

[16]  Shih-Fu Chang,et al.  Semi-Supervised Hashing for Large-Scale Search , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Rui Liu,et al.  Discrete Factorization Machines for Fast Feature-based Recommendation , 2018, IJCAI.

[18]  Yoram Singer,et al.  Local Low-Rank Matrix Approximation , 2013, ICML.

[19]  Wei Liu,et al.  Classification by Retrieval: Binarizing Data and Classifiers , 2017, SIGIR.

[20]  David A. McAllester,et al.  Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence , 2009, UAI 2009.

[21]  Johan Håstad,et al.  Some optimal inapproximability results , 2001, JACM.

[22]  Xin Wang,et al.  Social Recommendation with Strong and Weak Ties , 2016, CIKM.

[23]  Tao Jin,et al.  Collaborative topic regression for online recommender systems: an online and Bayesian approach , 2017, Machine Learning.

[24]  Patrick Seemann,et al.  Matrix Factorization Techniques for Recommender Systems , 2014 .

[25]  Yizhou Sun,et al.  Learning K-way D-dimensional Discrete Code For Compact Embedding Representations , 2017, ICML.

[26]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[27]  Ole Winther,et al.  Hash Embeddings for Efficient Word Representations , 2017, NIPS.

[28]  Alexander J. Smola,et al.  Collaborative Filtering on a Budget , 2010, AISTATS.

[29]  Matthew P. Wand,et al.  Kernel Smoothing , 1995 .

[30]  Hongyuan Zha,et al.  Learning binary codes for collaborative filtering , 2012, KDD.

[31]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[32]  Guowu Yang,et al.  Discrete Personalized Ranking for Fast Collaborative Filtering from Implicit Feedback , 2017, AAAI.

[33]  Huanbo Luan,et al.  Discrete Collaborative Filtering , 2016, SIGIR.

[34]  Michael I. Jordan,et al.  Distance Metric Learning with Application to Clustering with Side-Information , 2002, NIPS.

[35]  Jaana Kekäläinen,et al.  IR evaluation methods for retrieving highly relevant documents , 2000, SIGIR Forum.

[36]  Mohan S. Kankanhalli,et al.  Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews , 2018, WWW.

[37]  Xin Wang,et al.  Interactive Social Recommendation , 2017, CIKM.

[38]  Xianglong Liu,et al.  Collaborative Hashing , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.