Improving the Estimation of Tail Ratings in Recommender System with Multi-Latent Representations

The importance of the distribution of ratings on recommender systems (RS) is well-recognized. And yet, recommendation approaches based on latent factor models and recently introduced neural variants (e.g., NCF) optimize for the head of these distributions, potentially leading to large estimation errors for tail ratings. These errors in tail ratings that are far from the mean predicted rating fall out of a uni-modal assumption underlying these popular models, as we show in this paper. We propose to improve the estimation of tail ratings by extending traditional single latent representations (e.g., an item is represented by a single latent vector) with new multi-latent representations for better modeling these tail ratings. We show how to incorporate these multi-latent representations in an end-to-end neural prediction model that is designed to better reflect the underlying ratings distributions of items. Through experiments over six datasets, we find the proposed model leads to a significant improvement in RMSE versus a suite of benchmark methods. We also find that the predictions for the most polarized items are improved by more than 15%.

[1]  Chris Cornelis,et al.  Gradual trust and distrust in recommender systems , 2009, Fuzzy Sets Syst..

[2]  Barry Smyth,et al.  Trust in recommender systems , 2005, IUI.

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

[4]  Nitish Srivastava,et al.  Multimodal learning with deep Boltzmann machines , 2012, J. Mach. Learn. Res..

[5]  Liang He,et al.  A Hybrid Recommender Approach Based on Widrow-Hoff Learning , 2008, 2008 Second International Conference on Future Generation Communication and Networking.

[6]  James Caverlee,et al.  Recurrent Recommendation with Local Coherence , 2019, WSDM.

[7]  MengChu Zhou,et al.  A Nonnegative Latent Factor Model for Large-Scale Sparse Matrices in Recommender Systems via Alternating Direction Method , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[8]  Dinggang Shen,et al.  Deep Adversarial Learning for Multi-Modality Missing Data Completion , 2018, KDD.

[9]  Macarena Espinilla,et al.  REJA: A Georeferenced Hybrid Recommender System for Restaurants , 2009, 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology.

[10]  Mahsa Badami,et al.  Peeking into the other half of the glass : handling polarization in recommender systems. , 2017 .

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

[12]  Christoph Schlieder,et al.  A Spatial User Similarity Measure for Geographic Recommender Systems , 2009, GeoS.

[13]  Scott Sanner,et al.  AutoRec: Autoencoders Meet Collaborative Filtering , 2015, WWW.

[14]  Chris Cornelis,et al.  A Comparative Analysis of Trust-Enhanced Recommenders for Controversial Items , 2009, ICWSM.

[15]  J. Bobadilla,et al.  Recommender systems survey , 2013, Knowl. Based Syst..

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

[17]  Paolo Avesani,et al.  Trust-aware recommender systems , 2007, RecSys '07.

[18]  Panayiotis Tsaparas,et al.  Temporal mechanisms of polarization in online reviews , 2016, 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[19]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[20]  Ashish Sharma,et al.  An Adversarial Approach to Improve Long-Tail Performance in Neural Collaborative Filtering , 2018, CIKM.

[21]  Yang Yang,et al.  Start from Scratch: Towards Automatically Identifying, Modeling, and Naming Visual Attributes , 2014, ACM Multimedia.

[22]  D. Isenberg.  Group polarization: A critical review and meta-analysis. , 1986 .

[23]  Yongtae Woo,et al.  A Hybrid Recommender System Combining Collaborative Filtering with Neural Network , 2002, AH.

[24]  Hanning Zhou,et al.  A Neural Autoregressive Approach to Collaborative Filtering , 2016, ICML.

[25]  John R. Anderson,et al.  Beyond Globally Optimal: Focused Learning for Improved Recommendations , 2017, WWW.

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

[27]  F. Maxwell Harper,et al.  The MovieLens Datasets: History and Context , 2016, TIIS.

[28]  Paul A. Pavlou,et al.  Overcoming the J-shaped distribution of product reviews , 2009, CACM.

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

[30]  Yain-Whar Si,et al.  Design of a recommender system for mobile tourism multimedia selection , 2008, 2008 2nd International Conference on Internet Multimedia Services Architecture and Applications.

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

[32]  Julian J. McAuley,et al.  Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering , 2016, WWW.

[33]  Gediminas Adomavicius,et al.  Impact of data characteristics on recommender systems performance , 2012, TMIS.

[34]  Jennifer Golbeck,et al.  Generating Predictive Movie Recommendations from Trust in Social Networks , 2006, iTrust.

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

[36]  Kyong Joo Oh,et al.  The collaborative filtering recommendation based on SOM cluster-indexing CBR , 2003, Expert Syst. Appl..

[37]  Oren Barkan,et al.  ITEM2VEC: Neural item embedding for collaborative filtering , 2016, 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP).

[38]  Jaana Kekäläinen,et al.  Cumulated gain-based evaluation of IR techniques , 2002, TOIS.