KGWD: Knowledge Graph Based Wide & Deep Framework for Recommendation

Kemeng Liu, Zhonghong Ou, Yanxin Tan, Kai Zhao, Meina Song

Abstract: Knowledge Graph (KG) contains rich real-world auxiliary information, which can be leveraged to improve the performance of recommender systems. Nevertheless, existing recommender systems usually sample and aggregate neighbor entities and relations that link to target items to enrich the representations of items or users, whereas ignoring combinatorial features among different neighbor entities and relations. To resolve the problem mentioned above, we propose an end-to-end Knowledge Graph based Wide & Deep (KGWD) framework to leverage combinatorial features effectively. At the wide level, KGWD introduces a novel Triplet Compressed Interaction Network (TriCIN) to generate high-order combinatorial features among different triplets associated with the target item automatically. At the deep level, KGWD discovers users’ potential long-distance preferences by mining multi-hop neighbor information over the KG. We conduct experiments on three real-world datasets, i.e., Yelp2018, Last-FM, and Amazon-book, to evaluate the performance of KGWD. Experimental results demonstrate that KGWD outperforms state-of-the-art schemes significantly. Specifically, in all three datasets, KGWD improves the F1-score by more than 5% over the state-of-the-art.

External IDs:dblp:conf/apweb/LiuOTZS20