File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Social Recommendation with Self-Supervised Metagraph Informax Network

TitleSocial Recommendation with Self-Supervised Metagraph Informax Network
Authors
Keywordsgraph neural network
self-supervised learning
social recommendation
Issue Date2021
Citation
International Conference on Information and Knowledge Management, Proceedings, 2021, p. 1160-1169 How to Cite?
AbstractIn recent years, researchers attempt to utilize online social information to alleviate data sparsity for collaborative filtering, based on the rationale that social networks offers the insights to understand the behavioral patterns. However, due to the overlook of inter-dependent knowledge across items (e.g., knowledge graph dependencies between products), existing social recommender systems are insufficient to distill the heterogeneous collaborative signals from both user and item side. In this work, we propose Self- Supervised Metagraph Informax Network (SMIN) which investigates the potential of jointly incorporating social- and knowledge-aware relational structures into the user preference representation framework. To model relation heterogeneity, we design a metapath-guided heterogeneous graph neural network to aggregate feature embeddings from different types of meta-relations across users and items, empowering SMIN to maintain dedicated representations for multifaceted user- and item-wise dependencies. Additionally, to inject high-order collaborative signals into recommendation, we generalize the mutual information learning paradigm from vector space to a self-supervised graph-based collaborative filtering. This endows the expressive modeling of user-item interactive patterns, by exploring global-level collaborative relations and underlying isomorphic transformation property of graph topology. Experimental results on several real-world datasets demonstrate the effectiveness of our model over various state-of-the-art recommendation methods. Further analysis provides insights into the performance superiority of our new recommendation framework. We release our source code at https://github.com/SocialRecsys/SMIN.
Persistent Identifierhttp://hdl.handle.net/10722/308686
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLong, Xiaoling-
dc.contributor.authorHuang, Chao-
dc.contributor.authorXu, Yong-
dc.contributor.authorXu, Huance-
dc.contributor.authorDai, Peng-
dc.contributor.authorXia, Lianghao-
dc.contributor.authorBo, Liefeng-
dc.date.accessioned2021-12-08T07:49:55Z-
dc.date.available2021-12-08T07:49:55Z-
dc.date.issued2021-
dc.identifier.citationInternational Conference on Information and Knowledge Management, Proceedings, 2021, p. 1160-1169-
dc.identifier.urihttp://hdl.handle.net/10722/308686-
dc.description.abstractIn recent years, researchers attempt to utilize online social information to alleviate data sparsity for collaborative filtering, based on the rationale that social networks offers the insights to understand the behavioral patterns. However, due to the overlook of inter-dependent knowledge across items (e.g., knowledge graph dependencies between products), existing social recommender systems are insufficient to distill the heterogeneous collaborative signals from both user and item side. In this work, we propose Self- Supervised Metagraph Informax Network (SMIN) which investigates the potential of jointly incorporating social- and knowledge-aware relational structures into the user preference representation framework. To model relation heterogeneity, we design a metapath-guided heterogeneous graph neural network to aggregate feature embeddings from different types of meta-relations across users and items, empowering SMIN to maintain dedicated representations for multifaceted user- and item-wise dependencies. Additionally, to inject high-order collaborative signals into recommendation, we generalize the mutual information learning paradigm from vector space to a self-supervised graph-based collaborative filtering. This endows the expressive modeling of user-item interactive patterns, by exploring global-level collaborative relations and underlying isomorphic transformation property of graph topology. Experimental results on several real-world datasets demonstrate the effectiveness of our model over various state-of-the-art recommendation methods. Further analysis provides insights into the performance superiority of our new recommendation framework. We release our source code at https://github.com/SocialRecsys/SMIN.-
dc.languageeng-
dc.relation.ispartofInternational Conference on Information and Knowledge Management, Proceedings-
dc.subjectgraph neural network-
dc.subjectself-supervised learning-
dc.subjectsocial recommendation-
dc.titleSocial Recommendation with Self-Supervised Metagraph Informax Network-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1145/3459637.3482480-
dc.identifier.scopuseid_2-s2.0-85119174815-
dc.identifier.spage1160-
dc.identifier.epage1169-
dc.identifier.isiWOS:001054156201022-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats