Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences

17 Feb 2019Yixin CaoXiang WangXiangnan HeZikun huTat-Seng Chua

Incorporating knowledge graph (KG) into recommender system is promising in improving the recommendation accuracy and explainability. However, existing methods largely assume that a KG is complete and simply transfer the "knowledge" in KG at the shallow level of entity raw data or embeddings... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Recommendation Systems DBbook2014 KTUP (soft) [email protected] 0.3461 # 1
NDCG 0.2762 # 1
Knowledge Graph Completion DBbook2014 KTUP (soft) [email protected] 60.75 # 1
Mean Rank 499 # 1
Recommendation Systems MovieLens 1M KTUP (soft) [email protected] 0.8903 # 1
NDCG 0.6992 # 1
Knowledge Graph Completion MovieLens 1M KTUP (soft) [email protected] 48.9 # 1
Mean Rank 527 # 1