Neural Personalized Ranking for Image Recommendation Conference Paper uri icon

abstract

  • 2018 Association for Computing Machinery. We propose a new model toward improving the quality of image recommendations in social sharing communities like Pinterest, Flickr, and Instagram. Concretely, we propose Neural Personalized Ranking (NPR) - a personalized pairwise ranking model over implicit feedback datasets - that is inspired by Bayesian Personalized Ranking (BPR) and recent advances in neural networks. We further build an enhanced model by augmenting the basic NPR model with multiple contextual preference clues including user tags, geographic features, and visual factors. In our experiments over the Flickr YFCC100M dataset, we demonstrate the proposed NPR model is more effective than multiple baselines. Moreover, the contextual enhanced NPR model significantly outperforms the base model by 16.6% and a contextual enhanced BPR model by 4.5% in precision and recall.

name of conference

  • Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining

published proceedings

  • WSDM'18: PROCEEDINGS OF THE ELEVENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING

author list (cited authors)

  • Niu, W., Caverlee, J., & Lu, H.

citation count

  • 69

complete list of authors

  • Niu, Wei||Caverlee, James||Lu, Haokai

editor list (cited editors)

  • Chang, Y. i., Zhai, C., Liu, Y., & Maarek, Y.

publication date

  • February 2018