How to make latent factors interpretable by feeding Factorization machines with knowledge graphs

Model-based approaches to recommendation can recommend items with a very high level of accuracy. Unfortunately, even when the model embeds content-based information, if we move to a latent space we miss references to the actual semantics of recommended items. Consequently, this makes non-trivial the interpretation of a recommendation process. In this paper, we show how to initialize latent factors in Factorization Machines by using semantic features coming from a knowledge graph in order to train an interpretable model. With our model, semantic features are injected into the learning process to retain the original informativeness of the items available in the dataset. The accuracy and effectiveness of the trained model have been tested using two well-known recommender systems datasets. By relying on the information encoded in the original knowledge graph, we have also evaluated the semantic accuracy and robustness for the knowledge-aware interpretability of the final model.

[1]  Olfa Nasraoui,et al.  Explainable Matrix Factorization for Collaborative Filtering , 2016, WWW.

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

[3]  Jamal Bentahar,et al.  Specification and automatic verification of trust-based multi-agent systems , 2018, Future Gener. Comput. Syst..

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

[5]  Rashmi R. Sinha,et al.  The role of transparency in recommender systems , 2002, CHI Extended Abstracts.

[6]  Olfa Nasraoui,et al.  Explainable Restricted Boltzmann Machines for Collaborative Filtering , 2016, ArXiv.

[7]  Markus Zanker,et al.  Linked open data to support content-based recommender systems , 2012, I-SEMANTICS '12.

[8]  Paolo Tomeo,et al.  An Analysis on Time- and Session-aware Diversification in Recommender Systems , 2017, UMAP.

[9]  Arpit Rana,et al.  Explanation Chains: Recommendations by Explanation , 2017, RecSys Posters.

[10]  Iván Cantador,et al.  Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols , 2013, User Modeling and User-Adapted Interaction.

[11]  Guokun Lai,et al.  Daily-Aware Personalized Recommendation based on Feature-Level Time Series Analysis , 2015, WWW.

[12]  Xu Chen,et al.  Explainable Recommendation: A Survey and New Perspectives , 2018, Found. Trends Inf. Retr..

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

[14]  Lars Schmidt-Thieme,et al.  Fast context-aware recommendations with factorization machines , 2011, SIGIR.

[15]  Lars Schmidt-Thieme,et al.  Factorizing personalized Markov chains for next-basket recommendation , 2010, WWW '10.

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

[17]  Gediminas Adomavicius,et al.  Context-aware recommender systems , 2008, RecSys '08.

[18]  Judith Masthoff,et al.  Designing and Evaluating Explanations for Recommender Systems , 2011, Recommender Systems Handbook.

[19]  Alessandro Bozzon,et al.  Recurrent knowledge graph embedding for effective recommendation , 2018, RecSys.

[20]  Tommaso Di Noia,et al.  Exploiting the web of data in model-based recommender systems , 2012, RecSys.

[21]  Longbing Cao,et al.  Interpretable Recommendation via Attraction Modeling: Learning Multilevel Attractiveness over Multimodal Movie Contents , 2018, IJCAI.

[22]  Johannes Fürnkranz,et al.  Unsupervised generation of data mining features from linked open data , 2012, WIMS '12.

[23]  Steffen Rendle,et al.  Context-Aware Ranking with Factorization Models , 2010, Studies in Computational Intelligence.

[24]  John Riedl,et al.  Explaining collaborative filtering recommendations , 2000, CSCW '00.

[25]  Xu Chen,et al.  Learning to Rank Features for Recommendation over Multiple Categories , 2016, SIGIR.

[26]  Tat-Seng Chua,et al.  Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks , 2017, IJCAI.

[27]  Bing Liu,et al.  Aspect Based Recommendations: Recommending Items with the Most Valuable Aspects Based on User Reviews , 2017, KDD.

[28]  Roberto Turrin,et al.  Performance of recommender algorithms on top-n recommendation tasks , 2010, RecSys '10.

[29]  Michael J. Pazzani,et al.  Content-Based Recommendation Systems , 2007, The Adaptive Web.

[30]  Guokun Lai,et al.  Explicit factor models for explainable recommendation based on phrase-level sentiment analysis , 2014, SIGIR.

[31]  Gediminas Adomavicius,et al.  Multi-Criteria Recommender Systems , 2011, Recommender Systems Handbook.

[32]  Lora Aroyo,et al.  The effects of transparency on trust in and acceptance of a content-based art recommender , 2008, User Modeling and User-Adapted Interaction.

[33]  Markus Zanker.  The influence of knowledgeable explanations on users' perception of a recommender system , 2012, RecSys '12.

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

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

[36]  Liwei Wang,et al.  Exploring demographic information in social media for product recommendation , 2015, Knowledge and Information Systems.

[37]  Alessandro Sapienza,et al.  The Relevance of Categories for Trusting Information Sources , 2015, ACM Trans. Internet Techn..

[38]  Tommaso Di Noia,et al.  Ontology-based Linked Data Summarization in Semantics-aware Recommender Systems , 2018, SEBD.

[39]  Judith Masthoff,et al.  A Survey of Explanations in Recommender Systems , 2007, 2007 IEEE 23rd International Conference on Data Engineering Workshop.

[40]  Paolo Tomeo,et al.  Addressing the user cold start with cross-domain collaborative filtering: exploiting item metadata in matrix factorization , 2019, User Modeling and User-Adapted Interaction.

[41]  Alun D. Preece,et al.  Interpretability of deep learning models: A survey of results , 2017, 2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI).

[42]  Guy Shani,et al.  Evaluating Recommender Systems , 2015, Recommender Systems Handbook.

[43]  Tat-Seng Chua,et al.  TEM: Tree-enhanced Embedding Model for Explainable Recommendation , 2018, WWW.

[44]  Amit Dhurandhar,et al.  Building an Interpretable Recommender via Loss-Preserving Transformation , 2016, ArXiv.

[45]  Lars Schmidt-Thieme,et al.  Pairwise interaction tensor factorization for personalized tag recommendation , 2010, WSDM '10.

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

[47]  Jun Wang,et al.  Explanation Mining: Post Hoc Interpretability of Latent Factor Models for Recommendation Systems , 2018, KDD.

[48]  Bamshad Mobasher,et al.  Incorporating Context Correlation into Context-aware Matrix Factorization , 2015, CPCR+ITWP@IJCAI.

[49]  John Riedl,et al.  Tagsplanations: explaining recommendations using tags , 2009, IUI.