A Framework for Enhancing Deep Learning Based Recommender Systems with Knowledge Graphs. Mudur, S. P, Mokhov, S. A, & Mao, Y. In IDEAS 2021, pages 11–20, New York, NY, USA, July, 2021. Association for Computing Machinery. Journal Abbreviation: IDEAS 2021
A Framework for Enhancing Deep Learning Based Recommender Systems with Knowledge Graphs [link]Paper  doi  abstract   bibtex   
Recommendation methods fall into three major categories, content based filtering, collaborative filtering and deep learning based. Information about products and the preferences of earlier users are used in an unsupervised manner to create models which help make personalized recommendations to a specific new user. The more information we provide to these methods, the more likely it is that they yield better recommendations. Deep learning based methods are relatively recent, and are generally more robust to noise and missing information. This is because deep learning models can be trained even when some of the information records have partial information. Knowledge graphs represent the current trend in recording information in the form of relations between entities, and can provide any available information about products and users. This information is used to train the recommendation model. In this work, we present a new generic recommender systems framework, that integrates knowledge graphs into the recommendation pipeline. We describe its design and implementation, and then show through experiments, how such a framework can be specialized, taking the domain of movies as an example, and the resulting improvements in recommendations made possible by using all the information obtained using knowledge graphs. Our framework, to be made publicly available, supports different knowledge graph representation formats, and facilitates format conversion, merging and information extraction needed for training recommendation models.
@inproceedings{mudur_framework_2021,
	address = {New York, NY, USA},
	title = {A {Framework} for {Enhancing} {Deep} {Learning} {Based} {Recommender} {Systems} with {Knowledge} {Graphs}},
	url = {https://doi.org/10.1145/3472163.3472183},
	doi = {10.1145/3472163.3472183},
	abstract = {Recommendation methods fall into three major categories, content based
filtering, collaborative filtering and deep learning based. Information
about products and the preferences of earlier users are used in an
unsupervised manner to create models which help make personalized
recommendations to a specific new user. The more information we provide to
these methods, the more likely it is that they yield better
recommendations. Deep learning based methods are relatively recent, and
are generally more robust to noise and missing information. This is
because deep learning models can be trained even when some of the
information records have partial information. Knowledge graphs represent
the current trend in recording information in the form of relations
between entities, and can provide any available information about products
and users. This information is used to train the recommendation model. In
this work, we present a new generic recommender systems framework, that
integrates knowledge graphs into the recommendation pipeline. We describe
its design and implementation, and then show through experiments, how such
a framework can be specialized, taking the domain of movies as an example,
and the resulting improvements in recommendations made possible by using
all the information obtained using knowledge graphs. Our framework, to be
made publicly available, supports different knowledge graph representation
formats, and facilitates format conversion, merging and information
extraction needed for training recommendation models.},
	urldate = {2021-09-14},
	booktitle = {{IDEAS} 2021},
	publisher = {Association for Computing Machinery},
	author = {Mudur, Sudhir P and Mokhov, Serguei A and Mao, Yuhao},
	month = jul,
	year = {2021},
	note = {Journal Abbreviation: IDEAS 2021},
	keywords = {framework, knowledge graphs, recommendation model training, recommender system, deep learning based recommendations},
	pages = {11--20},
}

Downloads: 0