GAN-based Recommendation with Positive-Unlabeled Sampling

Recommender systems are popular tools for information retrieval tasks on a large variety of web applications and personalized products. In this work, we propose a Generative Adversarial Network based recommendation framework using a positive-unlabeled sampling strategy. Specifically, we utilize the generator to learn the continuous distribution of user-item tuples and design the discriminator to be a binary classifier that outputs the relevance score between each user and each item. Meanwhile, positive-unlabeled sampling is applied in the learning procedure of the discriminator. Theoretical bounds regarding positive-unlabeled sampling and optimalities of convergence for the discriminators and the generators are provided. We show the effectiveness and efficiency of our framework on three publicly accessible data sets with eight ranking-based evaluation metrics in comparison with thirteen popular baselines.

[1]  Minyi Guo,et al.  GraphGAN: Graph Representation Learning with Generative Adversarial Nets , 2017, AAAI.

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

[3]  Chuan Shi,et al.  Adversarial Learning on Heterogeneous Information Networks , 2019, KDD.

[4]  Paul Covington,et al.  Deep Neural Networks for YouTube Recommendations , 2016, RecSys.

[5]  Jesse Davis,et al.  Learning from positive and unlabeled data: a survey , 2018, Machine Learning.

[6]  Gang Niu,et al.  Positive-Unlabeled Learning with Non-Negative Risk Estimator , 2017, NIPS.

[7]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[8]  Nagarajan Natarajan,et al.  PU Learning for Matrix Completion , 2014, ICML.

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

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

[11]  Malik Yousef,et al.  One-Class SVMs for Document Classification , 2002, J. Mach. Learn. Res..

[12]  Gang Niu,et al.  Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning , 2016, NIPS.

[13]  Jung-Tae Lee,et al.  CFGAN: A Generic Collaborative Filtering Framework based on Generative Adversarial Networks , 2018, CIKM.

[14]  Xiaojin Zhu,et al.  Semi-Supervised Learning , 2010, Encyclopedia of Machine Learning.

[15]  Weinan Zhang,et al.  LambdaFM: Learning Optimal Ranking with Factorization Machines Using Lambda Surrogates , 2016, CIKM.

[16]  Walid Krichene,et al.  On Sampled Metrics for Item Recommendation , 2020, KDD.

[17]  Da Xu,et al.  Knowledge-aware Complementary Product Representation Learning , 2019, WSDM.

[18]  T. Hastie,et al.  Presence‐Only Data and the EM Algorithm , 2009, Biometrics.

[19]  Chee Keong Kwoh,et al.  Positive-unlabeled learning for disease gene identification , 2012, Bioinform..

[20]  MengChu Zhou,et al.  An Efficient Non-Negative Matrix-Factorization-Based Approach to Collaborative Filtering for Recommender Systems , 2014, IEEE Transactions on Industrial Informatics.

[21]  Gregory N. Hullender,et al.  Learning to rank using gradient descent , 2005, ICML.

[22]  Steffen Rendle,et al.  Factorization Machines , 2010, 2010 IEEE International Conference on Data Mining.

[23]  Heng-Tze Cheng,et al.  Wide & Deep Learning for Recommender Systems , 2016, DLRS@RecSys.

[24]  Dietmar Jannach,et al.  Measuring the Business Value of Recommender Systems , 2019, ACM Trans. Manag. Inf. Syst..

[25]  Jinfeng Yi,et al.  Scalable Demand-Aware Recommendation , 2017, NIPS.

[26]  Tat-Seng Chua,et al.  Neural Collaborative Filtering , 2017, WWW.

[27]  Gang Niu,et al.  Analysis of Learning from Positive and Unlabeled Data , 2014, NIPS.

[28]  Dacheng Tao,et al.  On Positive-Unlabeled Classification in GAN , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Rémi Gilleron,et al.  Learning from positive and unlabeled examples , 2000, Theor. Comput. Sci..

[30]  Rémi Gilleron,et al.  Positive and Unlabeled Examples Help Learning , 1999, ALT.

[31]  Peng Zhang,et al.  IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models , 2017, SIGIR.

[32]  Charles Elkan,et al.  Learning classifiers from only positive and unlabeled data , 2008, KDD.

[33]  Yunming Ye,et al.  DeepFM: A Factorization-Machine based Neural Network for CTR Prediction , 2017, IJCAI.

[34]  Wenkai Li,et al.  A Positive and Unlabeled Learning Algorithm for One-Class Classification of Remote-Sensing Data , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[35]  Siu Cheung Hui,et al.  Multi-Pointer Co-Attention Networks for Recommendation , 2018, KDD.

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

[37]  Srujana Merugu,et al.  A scalable collaborative filtering framework based on co-clustering , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[38]  Yi Tay,et al.  Deep Learning based Recommender System: A Survey and New Perspectives , 2018 .

[39]  Tat-Seng Chua,et al.  Neural Factorization Machines for Sparse Predictive Analytics , 2017, SIGIR.

[40]  Yehuda Koren,et al.  Factorization meets the neighborhood: a multifaceted collaborative filtering model , 2008, KDD.

[41]  Lantao Yu,et al.  SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient , 2016, AAAI.

[42]  Bernhard Schölkopf,et al.  Support Vector Method for Novelty Detection , 1999, NIPS.

[43]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[44]  Daniel Lemire,et al.  Slope One Predictors for Online Rating-Based Collaborative Filtering , 2007, SDM.