Vectors of Pairwise Item Preferences
Pandey, G., Wang, S., Ren, Z., & Chang, Y. (2019). Vectors of Pairwise Item Preferences. In L. Azzopardi, B. Stein, N. Fuhr, P. Mayr, C. Hauff, & D. Hiemstra (Eds.), ECIR 2019: Advances in Information Retrieval : 41st European Conference on IR Research, ECIR 2019, Cologne, Germany, April 14–-8, 2019, Proceedings, Part I (pp. 323-336). Springer. Lecture Notes in Computer Science, 11437. https://doi.org/10.1007/978-3-030-15712-8_21
Published in
Lecture Notes in Computer ScienceEditors
Date
2019Copyright
© Springer Nature Switzerland AG 2019
Neural embedding has been widely applied as an effective category of vectorization methods in real-world recommender systems. However, its exploration of users’ explicit feedback on items, to create good quality user and item vectors is still limited. Existing neural embedding methods only consider the items that are accessed by the users, but neglect the scenario when a user gives high or low rating to a particular item. In this paper, we propose Pref2Vec, a method to generate vector representations of pairwise item preferences, users and items, which can be directly utilized for machine learning tasks. Specifically, Pref2Vec considers users’ pairwise item preferences as elementary units. It vectorizes users’ pairwise preferences by maximizing the likelihood estimation of the conditional probability of each pairwise item preference given another one. With the pairwise preference matrix and the generated preference vectors, the vectors of users are yielded by minimizing the difference between users’ observed preferences and the product of the user and preference vectors. Similarly, the vectorization of items can be achieved with the user-item rating matrix and the users vectors. We conducted extensive experiments on three benchmark datasets to assess the quality of item vectors and the initialization independence of the user and item vectors. The utility of our vectorization results is shown by the recommendation performance achieved using them. Our experimental results show significant improvement over state-of-the-art baselines.
...


Publisher
SpringerParent publication ISBN
978-3-030-15711-1Conference
European Conference on Information RetrievalIs part of publication
ECIR 2019: Advances in Information Retrieval : 41st European Conference on IR Research, ECIR 2019, Cologne, Germany, April 14–-8, 2019, Proceedings, Part IISSN Search the Publication Forum
0302-9743Publication in research information system
https://converis.jyu.fi/converis/portal/detail/Publication/29722441
Metadata
Show full item recordCollections
License
Related items
Showing items with similar title or keywords.
-
Children’s Fruit and Vegetable Preferences Are Associated with Their Mothers’ and Fathers’ Preferences
Kähkönen, Kaisa; Sandell, Mari; Rönkä, Anna; Hujo, Mika; Nuutinen, Outi (MDPI AG, 2021)Children’s preference for fruit and vegetables must emerge during childhood. At children’s homes, mothers and fathers influence children’s developing food preferences with their own preferences and actions. The purpose of ... -
Customer personalization driven content management system
Bazanov, Ilia (2017)Customer information can be used to tailor products, services and consumption experiences to fit the specific needs and tastes of customers. Website personalization allows changing radically the attitude of a website for ... -
Recommending Serendipitous Items using Transfer Learning
Pandey, Gaurav; Kotkov, Denis; Semenov, Alexander (ACM Press, 2018)Most recommender algorithms are designed to suggest relevant items, but suggesting these items does not always result in user satisfaction. Therefore, the efforts in recommender systems recently shifted towards serendipity, ... -
Content Aware Music Analysis with Multi-Dimensional Similarity Measure
Wohlfahrt-Laymann, Jan; Heimbürger, Anneli (IOS Press, 2017)Music players and cloud solution for music recommendation and automatic playlist creation are becoming increasingly more popular, as they intent to overcome the issue of the difficulty for users to find fitting music, ...