[2009.04104v1] Rule-Guided Graph Neural Networks for Recommender Systemsopen searchopen navigation menucontact arXivsubscribe to arXiv mailings

To alleviate the cold start problem caused by collaborative filtering in recommender systems, knowledge graphs (KGs) are increasingly employed by many methods as auxiliary resources. However, existing work incorporated with KGs cannot capture the explicit long-range semantics between users and items meanwhile consider various connectivity between items. In this paper, we propose RGRec, which combines rule learning and graph neural networks (GNNs) for recommendation. RGRec first maps items to corresponding entities in KGs and adds users as new entities. Then, it automatically learns rules to model the explicit long-range semantics, and captures the connectivity between entities by aggregation to better encode various information. We show the effectiveness of RGRec on three real-world datasets. Particularly, the combination of rule learning and GNNs achieves substantial improvement compared to methods only using either of them.

1 mentions: @DanilBaibak
Date: 2020/09/17 09:52

Referring Tweets

@DanilBaibak Rule-Guided Graph Neural Networks for Recommender Systems. Combination of rule learning and GNNs achieves substantial improvement compared to methods only using either of them #RecommendationSystem #NeuralNetwork Paper: t.co/a7QOHsgAdi Github: t.co/v7zHkRx90e t.co/fSuJNcFYPi

Related Entries

Read more Building Machine Learning Models via Comparisons – Blog | Machine Learning | Carnegie Mellon Univers...
0 users, 15 mentions 2019/03/29 15:50
Read more GitHub - DanilBaibak/movie-recommendation-system: Building recommendation system based Bayesian Pers...
0 users, 1 mentions 2020/01/24 08:20
Read more L3 Flow Models -- CS294-158-SP20 Deep Unsupervised Learning -- UC Berkeley -- Spring 2020 - YouTube
0 users, 2 mentions 2020/04/06 05:21
Read more Machine Learning in Production using Apache Airflow
0 users, 1 mentions 2020/06/08 13:44
Read more [2009.06978] Dialogue Response Ranking Training with Large-Scale Human Feedback Dataopen searchopen ...
0 users, 2 mentions 2020/09/18 09:52