Journal
APPLIED INTELLIGENCE
Volume 52, Issue 6, Pages 6196-6207Publisher
SPRINGER
DOI: 10.1007/s10489-021-02647-1
Keywords
Knowledge graph; Autoencoder; Recommendation systems
Categories
Funding
- National Natural Science Foundation of China [61906060]
Ask authors/readers for more resources
This study proposes a personalized recommendation method PRKG, which extends item feature representations with Knowledge Graph, to address the issues of existing deep recommendation methods requiring a large amount of labeled data and scarce side information.
In the past decades, personalized recommendation systems have attracted a vast amount of attention and researches from multiple disciplines. Recently, for the powerful ability of feature representation learning, deep neural networks have achieved sound performance in the recommendation. However, most of the existing deep recommendation approaches require a large number of labeled data, which is often expensive and labor-some in applications. Meanwhile, the side information of users and items that can extend the feature space effectively is usually scarce. To address these problems, we propose a Personalized Recommendation method, which extends items' feature representations with Knowledge Graph via dual-autoencoder (short for PRKG). More specifically, we first extract items' side information from open knowledge graph like DBpedia as items' feature extension. Secondly, we learn the low-dimensional representations of additional features collected from DBpedia via the autoencoder module and then integrate the processed features into the original feature space. Finally, the reconstructed features is incorporated into the semi-autoencoder for personalized recommendations. Extensive experiments conducted on several real-world datasets validate the effectiveness of our proposed methods compared to several state-of-the-art models.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available