Collaborative Translational Metric Learning

4 Jun 2019  ·  Chanyoung Park, Donghyun Kim, Xing Xie, Hwanjo Yu ·

Recently, matrix factorization-based recommendation methods have been criticized for the problem raised by the triangle inequality violation. Although several metric learning-based approaches have been proposed to overcome this issue, existing approaches typically project each user to a single point in the metric space, and thus do not suffice for properly modeling the intensity and the heterogeneity of user-item relationships in implicit feedback. In this paper, we propose TransCF to discover such latent user-item relationships embodied in implicit user-item interactions. Inspired by the translation mechanism popularized by knowledge graph embedding, we construct user-item specific translation vectors by employing the neighborhood information of users and items, and translate each user toward items according to the user's relationships with the items. Our proposed method outperforms several state-of-the-art methods for top-N recommendation on seven real-world data by up to 17% in terms of hit ratio. We also conduct extensive qualitative evaluations on the translation vectors learned by our proposed method to ascertain the benefit of adopting the translation mechanism for implicit feedback-based recommendations.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Recommendation Systems Amazon C&A TransCF Hits@10 0.3436 # 1
Hits@20 0.4658 # 1
nDCG@10 0.2019 # 1
nDCG@20 0.2323 # 1
Recommendation Systems Book-Crossing TransCF Hits@10 0.3329 # 1
Hits@20 0.4744 # 1
nDCG@10 0.1865 # 1
nDCG@20 0.2221 # 1
Recommendation Systems Ciao TransCF Hits@10 0.2292 # 1
Hits@20 0.374 # 1
nDCG@10 0.1167 # 1
nDCG@20 0.1525 # 1
Recommendation Systems Declicious TransCF Hits@10 0.2586 # 1
Hits@20 0.3786 # 1
nDCG@10 0.1475 # 1
nDCG@20 0.1781 # 1
Recommendation Systems Flixster TransCF Hits@10 0.7309 # 1
Hits@20 0.8374 # 1
nDCG@10 0.4986 # 1
nDCG@20 0.5257 # 1
Recommendation Systems Pinterest TransCF nDCG@10 0.258 # 1
Hits@10 0.5504 # 1
Hits@20 0.8108 # 1
nDCG@20 0.3242 # 1
Recommendation Systems Tradesy TransCF Hits@10 0.3198 # 1
Hits@20 0.4505 # 1
nDCG@10 0.1767 # 1
nDCG@20 0.2095 # 1

Methods


No methods listed for this paper. Add relevant methods here