Simple and effective neural-free soft-cluster embeddings for item cold-start recommendations

Recommender systems are widely used in online platforms for easy exploration of personalized content. The best available recommendation algorithms are based on using the observed preference information among collaborating entities. A significant challenge in recommender system continues to be item cold-start recommendation: how to effectively recommend items with no observed or past preference information. Here we propose a two-stage algorithm based on soft clustering to provide an efficient solution to this problem. The crux of our approach lies in representing the items as soft-cluster embeddings in the space spanned by the side-information associated with the items. Though many item embedding approaches have been proposed for item cold-start recommendations in the past—and simple as they might appear—to the best of our knowledge, the approach based on soft-cluster embeddings has not been proposed in the research literature. Our experimental results on four benchmark datasets conclusively demonstrate that the proposed algorithm makes accurate recommendations in item cold-start settings compared to the state-of-the-art algorithms according to commonly used ranking metrics like Normalized Discounted Cumulative Gain (NDCG) and Mean Average Precision (MAP). The performance of our proposed algorithm on the MovieLens 20M dataset clearly demonstrates the scalability aspect of our algorithm compared to other popular algorithms. We also propose the metric Cold Items Precision (CIP) to quantify the ability of a system to recommend cold-start items. CIP can be used in conjunction with relevance ranking metrics like NDCG and MAP to measure the effectiveness of the cold-start recommendation algorithm.

[1]  Chris H. Q. Ding,et al.  On the Equivalence of Nonnegative Matrix Factorization and Spectral Clustering , 2005, SDM.

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

[3]  Tao Li,et al.  IFD: Iterative Feature and Data Clustering , 2004, SDM.

[4]  Tao Li,et al.  The Relationships Among Various Nonnegative Matrix Factorization Methods for Clustering , 2006, Sixth International Conference on Data Mining (ICDM'06).

[5]  Reinhard Heckel,et al.  Addressing Interpretability and Cold-Start in Matrix Factorization for Recommender Systems , 2019, IEEE Transactions on Knowledge and Data Engineering.

[6]  Prateek Jain,et al.  Non-convex Optimization for Machine Learning , 2017, Found. Trends Mach. Learn..

[7]  Dietmar Jannach,et al.  Are we really making much progress? A worrying analysis of recent neural recommendation approaches , 2019, RecSys.

[8]  Steffen Rendle,et al.  Factorization Machines with libFM , 2012, TIST.

[9]  Kai Chen,et al.  Collaborative Filtering and Deep Learning Based Hybrid Recommendation for Cold Start Problem , 2016, 2016 IEEE 14th Intl Conf on Dependable, Autonomic and Secure Computing, 14th Intl Conf on Pervasive Intelligence and Computing, 2nd Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech).

[10]  Geoffrey J. Gordon,et al.  Relational learning via collective matrix factorization , 2008, KDD.

[11]  Amin Mantrach,et al.  Item cold-start recommendations: learning local collective embeddings , 2014, RecSys '14.

[12]  Lars Schmidt-Thieme,et al.  Learning Attribute-to-Feature Mappings for Cold-Start Recommendations , 2010, 2010 IEEE International Conference on Data Mining.

[13]  Thomas Oberlin,et al.  Matrix Co-Factorization for Cold-Start Recommendation , 2018, ISMIR.

[14]  Tat-Seng Chua,et al.  Neural Graph Collaborative Filtering , 2019, SIGIR.

[15]  Oren Somekh,et al.  Budget-Constrained Item Cold-Start Handling in Collaborative Filtering Recommenders via Optimal Design , 2014, WWW.

[16]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[17]  Chris H. Q. Ding,et al.  Convex and Semi-Nonnegative Matrix Factorizations , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Boris Cule,et al.  Collaborative Filtering for Binary, Positiveonly Data , 2017, SKDD.

[19]  Hugo Larochelle,et al.  A Meta-Learning Perspective on Cold-Start Recommendations for Items , 2017, NIPS.

[20]  Elena Smirnova,et al.  Meta-Prod2Vec: Product Embeddings Using Side-Information for Recommendation , 2016, RecSys.

[21]  Yifan Hu,et al.  Collaborative Filtering for Implicit Feedback Datasets , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[22]  Srinivasan Parthasarathy,et al.  ColdRoute: effective routing of cold questions in stack exchange sites , 2018, Data Mining and Knowledge Discovery.

[23]  Jimmy J. Lin,et al.  The Neural Hype and Comparisons Against Weak Baselines , 2019, SIGIR Forum.

[24]  Freimut Bodendorf,et al.  Emotions and fashion recommendations: evaluating the predictive power of affective information for the prediction of fashion product preferences in cold-start scenarios , 2017, WI.

[25]  Jimmy J. Lin,et al.  Critically Examining the "Neural Hype": Weak Baselines and the Additivity of Effectiveness Gains from Neural Ranking Models , 2019, SIGIR.

[26]  Shuang-Hong Yang,et al.  Functional matrix factorizations for cold-start recommendation , 2011, SIGIR.

[27]  Wei Chu,et al.  Information Services]: Web-based services , 2022 .

[28]  Noemi Mauro,et al.  Performance comparison of neural and non-neural approaches to session-based recommendation , 2019, RecSys.

[29]  Martin Wattenberg,et al.  Ad click prediction: a view from the trenches , 2013, KDD.

[30]  Lars Schmidt-Thieme,et al.  Multi-relational matrix factorization using bayesian personalized ranking for social network data , 2012, WSDM '12.

[31]  Jie Tang,et al.  Addressing cold start in recommender systems: a semi-supervised co-training algorithm , 2014, SIGIR.

[32]  Lei Zheng,et al.  Spectral collaborative filtering , 2018, RecSys.

[33]  Yves Grandvalet,et al.  A Coverage-Based Approach to Recommendation Diversity On Similarity Graph , 2016, RecSys.

[34]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

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

[36]  M. Saquib Sarfraz,et al.  Efficient Parameter-Free Clustering Using First Neighbor Relations , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Scott Sanner,et al.  Low-Rank Linear Cold-Start Recommendation from Social Data , 2017, AAAI.

[38]  Harald Steck,et al.  Evaluation of recommendations: rating-prediction and ranking , 2013, RecSys.

[39]  D. Pham,et al.  Selection of K in K-means clustering , 2005 .

[40]  Florian Strub,et al.  Hybrid Collaborative Filtering with Autoencoders , 2016 .

[41]  Yi-Hsuan Yang,et al.  Addressing Cold Start for Next-song Recommendation , 2016, RecSys.

[42]  G. Dover,et al.  An analysis of fetal hemoglobin variation in sickle cell disease: the relative contributions of the X-linked factor, beta-globin haplotypes, alpha-globin gene number, gender, and age. , 1995, Blood.

[43]  Mohamed Nadif,et al.  A dynamic collaborative filtering system via a weighted clustering approach , 2016, Neurocomputing.

[44]  Oren Somekh,et al.  ExcUseMe: Asking Users to Help in Item Cold-Start Recommendations , 2015, RecSys.

[45]  Dietmar Jannach,et al.  Evaluation of session-based recommendation algorithms , 2018, User Modeling and User-Adapted Interaction.

[46]  Mikhail Belkin,et al.  Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples , 2006, J. Mach. Learn. Res..

[47]  Hayder Radha,et al.  Cold-Start Item and User Recommendation with Decoupled Completion and Transduction , 2015, RecSys.

[48]  Max Welling,et al.  Graph Convolutional Matrix Completion , 2017, ArXiv.