File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Joint modeling of local and global behavior dynamics for session-based recommendation

TitleJoint modeling of local and global behavior dynamics for session-based recommendation
Authors
Issue Date2020
PublisherIOS Press.
Citation
24th European Conference on Artificial Intelligence (ECAI 2020), Santiago de Compostela, Spain, 29 August-8 September 2020. In ECAI 2020: 24th European Conference on Artificial Intelligence 29 August–8 September 2020, Santiago de Compostela, Spain, p. 545-552. Amsterdam, Netherlands: IOS Press, 2020 How to Cite?
AbstractSession-based recommendation is critical in modern recommender systems, which aims to predict the next interested item given anonymous behavior sequences of users. While prior works have made efforts to addressing the session-based recommendation problem, two significant limitations exist: I) They ignore the fact that items may be correlated with other across different session units; ii) existing solutions are also limited in their assumption of rigidly ordered pattern over intra-session item transition, which may not be true in practice. To address these above limitations, we propose a Local-Global Session-based Recommendation framework-LGSR which generalizes the modeling of behavior dynamics from two perspectives: We first design a cross-session item dependency encoder to learn the inter-session item relation structures from a global perspective. Additionally, a dual-stage attentive aggregation module is developed to capture local item transition dynamics, without the restriction of rigid sequential process for jointly modeling user's current interest and intra-session purpose. With the exploration of both complex intra- and inter-session interest transitional regularities, our LGSR model enables the representation learning of user behavior dynamics via jointly mapping local and global signals into the same latent space. The experimental results on two real-world datasets demonstrate the superiority of the proposed LGSR framework over state-of-the-art methods.
Persistent Identifierhttp://hdl.handle.net/10722/308824
ISBN
ISSN
2023 SCImago Journal Rankings: 0.281
ISI Accession Number ID
Series/Report no.Frontiers in Artificial Intelligence and Applications ; 325

 

DC FieldValueLanguage
dc.contributor.authorXu, Yong-
dc.contributor.authorChen, Jiahui-
dc.contributor.authorHuang, Chao-
dc.contributor.authorZhang, Bo-
dc.contributor.authorXing, Hao-
dc.contributor.authorDai, Peng-
dc.contributor.authorBo, Liefeng-
dc.date.accessioned2021-12-08T07:50:12Z-
dc.date.available2021-12-08T07:50:12Z-
dc.date.issued2020-
dc.identifier.citation24th European Conference on Artificial Intelligence (ECAI 2020), Santiago de Compostela, Spain, 29 August-8 September 2020. In ECAI 2020: 24th European Conference on Artificial Intelligence 29 August–8 September 2020, Santiago de Compostela, Spain, p. 545-552. Amsterdam, Netherlands: IOS Press, 2020-
dc.identifier.isbn9781643681009-
dc.identifier.issn0922-6389-
dc.identifier.urihttp://hdl.handle.net/10722/308824-
dc.description.abstractSession-based recommendation is critical in modern recommender systems, which aims to predict the next interested item given anonymous behavior sequences of users. While prior works have made efforts to addressing the session-based recommendation problem, two significant limitations exist: I) They ignore the fact that items may be correlated with other across different session units; ii) existing solutions are also limited in their assumption of rigidly ordered pattern over intra-session item transition, which may not be true in practice. To address these above limitations, we propose a Local-Global Session-based Recommendation framework-LGSR which generalizes the modeling of behavior dynamics from two perspectives: We first design a cross-session item dependency encoder to learn the inter-session item relation structures from a global perspective. Additionally, a dual-stage attentive aggregation module is developed to capture local item transition dynamics, without the restriction of rigid sequential process for jointly modeling user's current interest and intra-session purpose. With the exploration of both complex intra- and inter-session interest transitional regularities, our LGSR model enables the representation learning of user behavior dynamics via jointly mapping local and global signals into the same latent space. The experimental results on two real-world datasets demonstrate the superiority of the proposed LGSR framework over state-of-the-art methods.-
dc.languageeng-
dc.publisherIOS Press.-
dc.relation.ispartofECAI 2020: 24th European Conference on Artificial Intelligence 29 August–8 September 2020, Santiago de Compostela, Spain-
dc.relation.ispartofseriesFrontiers in Artificial Intelligence and Applications ; 325-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.titleJoint modeling of local and global behavior dynamics for session-based recommendation-
dc.typeConference_Paper-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.3233/FAIA200137-
dc.identifier.scopuseid_2-s2.0-85091763796-
dc.identifier.spage545-
dc.identifier.epage552-
dc.identifier.isiWOS:000650971300069-
dc.publisher.placeAmsterdam, Netherlands-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats