File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Multi-behavior enhanced recommendation with cross-interaction collaborative relation modeling

TitleMulti-behavior enhanced recommendation with cross-interaction collaborative relation modeling
Authors
KeywordsGraph Neural Networks
Multi-Behavior Recommendation
Recommender Systems
Issue Date2021
Citation
Proceedings - International Conference on Data Engineering, 2021, v. 2021-April, p. 1931-1936 How to Cite?
AbstractMany previous studies aim to augment collaborative filtering with deep neural network techniques, so as to achieve better recommendation performance. However, most existing deep learning-based recommender systems are designed for modeling singular type of user-item interaction behavior, which can hardly distill the heterogeneous relations between user and item. In practical recommendation scenarios, there exist multi-typed user behaviors, such as browse and purchase. Due to the overlook of user's multi-behavioral patterns over different items, existing recommendation methods are insufficient to capture heterogeneous collaborative signals from user multi-behavior data. Inspired by the strength of graph neural networks for structured data modeling, this work proposes a Graph Neural Multi-Behavior Enhanced Recommendation (GNMR) framework which explicitly models the dependencies between different types of user-item interactions under a graph-based message passing architecture. GNMR devises a relation aggregation network to model interaction heterogeneity, and recursively performs embedding propagation between neighboring nodes over the user-item interaction graph. Experiments on real-world recommendation datasets show that our GNMR consistently outperforms state-of-the-art methods. The source code is available at https://github.com/akaxlh/GNMR.
Persistent Identifierhttp://hdl.handle.net/10722/308879
ISSN
2023 SCImago Journal Rankings: 1.306
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorXia, Lianghao-
dc.contributor.authorHuang, Chao-
dc.contributor.authorXu, Yong-
dc.contributor.authorDai, Peng-
dc.contributor.authorLu, Mengyin-
dc.contributor.authorBo, Liefeng-
dc.date.accessioned2021-12-08T07:50:19Z-
dc.date.available2021-12-08T07:50:19Z-
dc.date.issued2021-
dc.identifier.citationProceedings - International Conference on Data Engineering, 2021, v. 2021-April, p. 1931-1936-
dc.identifier.issn1084-4627-
dc.identifier.urihttp://hdl.handle.net/10722/308879-
dc.description.abstractMany previous studies aim to augment collaborative filtering with deep neural network techniques, so as to achieve better recommendation performance. However, most existing deep learning-based recommender systems are designed for modeling singular type of user-item interaction behavior, which can hardly distill the heterogeneous relations between user and item. In practical recommendation scenarios, there exist multi-typed user behaviors, such as browse and purchase. Due to the overlook of user's multi-behavioral patterns over different items, existing recommendation methods are insufficient to capture heterogeneous collaborative signals from user multi-behavior data. Inspired by the strength of graph neural networks for structured data modeling, this work proposes a Graph Neural Multi-Behavior Enhanced Recommendation (GNMR) framework which explicitly models the dependencies between different types of user-item interactions under a graph-based message passing architecture. GNMR devises a relation aggregation network to model interaction heterogeneity, and recursively performs embedding propagation between neighboring nodes over the user-item interaction graph. Experiments on real-world recommendation datasets show that our GNMR consistently outperforms state-of-the-art methods. The source code is available at https://github.com/akaxlh/GNMR.-
dc.languageeng-
dc.relation.ispartofProceedings - International Conference on Data Engineering-
dc.subjectGraph Neural Networks-
dc.subjectMulti-Behavior Recommendation-
dc.subjectRecommender Systems-
dc.titleMulti-behavior enhanced recommendation with cross-interaction collaborative relation modeling-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/ICDE51399.2021.00179-
dc.identifier.scopuseid_2-s2.0-85112867032-
dc.identifier.volume2021-April-
dc.identifier.spage1931-
dc.identifier.epage1936-
dc.identifier.isiWOS:000687830800171-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats