Collaborative Translational Metric Learning

4 Jun 2019Chanyoung ParkDonghyun KimXing XieHwanjo 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... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Recommendation Systems Amazon C&A TransCF [email protected] 0.3436 # 1
[email protected] 0.4658 # 1
[email protected] 0.2019 # 1
[email protected] 0.2323 # 1
Recommendation Systems Book-Crossing TransCF [email protected] 0.3329 # 1
[email protected] 0.4744 # 1
[email protected] 0.1865 # 1
[email protected] 0.2221 # 1
Recommendation Systems Ciao TransCF [email protected] 0.2292 # 1
[email protected] 0.374 # 1
[email protected] 0.1167 # 1
[email protected] 0.1525 # 1
Recommendation Systems Declicious TransCF [email protected] 0.2586 # 1
[email protected] 0.3786 # 1
[email protected] 0.1475 # 1
[email protected] 0.1781 # 1
Recommendation Systems Flixster TransCF [email protected] 0.7309 # 1
[email protected] 0.8374 # 1
[email protected] 0.4986 # 1
[email protected] 0.5257 # 1
Recommendation Systems Pinterest TransCF [email protected] 0.258 # 2
[email protected] 0.5504 # 1
[email protected] 0.8108 # 1
[email protected] 0.3242 # 1
Recommendation Systems Tradesy TransCF [email protected] 0.3198 # 1
[email protected] 0.4505 # 1
[email protected] 0.1767 # 1
[email protected] 0.2095 # 1