AUTHOR=Geng Yishuai , Xiao Xiao , Sun Xiaobing , Zhu Yi 

TITLE=Representation Learning: Recommendation With Knowledge Graph via Triple-Autoencoder

JOURNAL=Frontiers in Genetics

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2022.891265

DOI=10.3389/fgene.2022.891265

ISSN=1664-8021

ABSTRACT=The last decades have witnessed a vast amount of interest and research in feature representation learning from multiple disciplines, such as Biology, Bioinformation. Among all the real-world application scenarios, feature extraction from Knowledge Graph (KG) for personalized recommendation has achieved substantial performance for addressing the problem of information over-loaded. However, the rating matrix of recommendation is usually sparse which may result in significant performance degradation, the crucial problem is how to extract and extend features from additional side information. To address these problems, in this paper, we propose a novel feature representation learning method for the recommendation, which extends items features with Knowledge Graph via triple-autoencoder. More specifically, the comment information between users and items are firstly encoded as sentiment classification, these features are then applied as the input to autoencoder for generating the auxiliary information of items. Secondly, the item-based rating, the side information, and the generated comment representations are incorporated into the semi-autoencoder for reconstructed output, the low-dimensional representations of these extended information are learned with semi-autoencoder. Finally, the reconstructed output generated by the semi-autoencoder are input into a third autoencoder, a serial connection of the semi-autoencoder and autoencoder is designed here to learn more abstract and higher-level feature representations for personalized recommendation. Extensive experiments conducted on several real-world datasets validate the effectiveness of our proposed method compared to several state-of-the-art models.