Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380077612> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4380077612 abstract "For click-through rate (CTR) prediction tasks, a good prediction performance can be obtained by full explorations of both user behavior and item behavior. Since user’s interests have a great influence on user’s behaviors, it is very important to learn users’ intrinsic interests according to their behaviors. User interests are not only diverse but also in dynamic change. However, the dynamics of user interests’ change are not fully taken into account by the majority of current CTR models. The latest sequential recommendation algorithm ignores the subjectivity of users when it uses a two-layer recurrent neural network to model the item behavior from the perspective of the evolution of items. In this work, we propose a recurrent neural network model called DTIAN (Deep Time-Aware Interest Attention Network) to address these issues. By leveraging the user behaviors and the corresponding temporal information, DTIAN captures user interests and intent changes to the target item. Therefore, the users’ recent interests are enhanced compared to early interests with the attention mechanism. In addition, each module of the proposed model can be plugged into other mainstream models to improve the performance of current models. The experimental results show that the proposed DTIAN can outperform the current popular CTR prediction models slightly and significantly reduce the training time, which makes it possible to implement lightweight models." @default.
- W4380077612 created "2023-06-10" @default.
- W4380077612 creator A5015878118 @default.
- W4380077612 creator A5018560081 @default.
- W4380077612 creator A5064830115 @default.
- W4380077612 creator A5067029799 @default.
- W4380077612 creator A5086290413 @default.
- W4380077612 date "2023-07-18" @default.
- W4380077612 modified "2023-10-06" @default.
- W4380077612 title "Deep Time-Aware Attention Neural Network for Sequential Recommendation" @default.
- W4380077612 cites W1678356000 @default.
- W4380077612 cites W1985759455 @default.
- W4380077612 cites W2512971201 @default.
- W4380077612 cites W2783272285 @default.
- W4380077612 cites W2963367478 @default.
- W4380077612 cites W2963493749 @default.
- W4380077612 cites W3098024612 @default.
- W4380077612 doi "https://doi.org/10.1142/s0217595923400201" @default.
- W4380077612 hasPublicationYear "2023" @default.
- W4380077612 type Work @default.
- W4380077612 citedByCount "0" @default.
- W4380077612 crossrefType "journal-article" @default.
- W4380077612 hasAuthorship W4380077612A5015878118 @default.
- W4380077612 hasAuthorship W4380077612A5018560081 @default.
- W4380077612 hasAuthorship W4380077612A5064830115 @default.
- W4380077612 hasAuthorship W4380077612A5067029799 @default.
- W4380077612 hasAuthorship W4380077612A5086290413 @default.
- W4380077612 hasConcept C119857082 @default.
- W4380077612 hasConcept C12713177 @default.
- W4380077612 hasConcept C138885662 @default.
- W4380077612 hasConcept C147168706 @default.
- W4380077612 hasConcept C154945302 @default.
- W4380077612 hasConcept C27206212 @default.
- W4380077612 hasConcept C2777617010 @default.
- W4380077612 hasConcept C41008148 @default.
- W4380077612 hasConcept C50644808 @default.
- W4380077612 hasConceptScore W4380077612C119857082 @default.
- W4380077612 hasConceptScore W4380077612C12713177 @default.
- W4380077612 hasConceptScore W4380077612C138885662 @default.
- W4380077612 hasConceptScore W4380077612C147168706 @default.
- W4380077612 hasConceptScore W4380077612C154945302 @default.
- W4380077612 hasConceptScore W4380077612C27206212 @default.
- W4380077612 hasConceptScore W4380077612C2777617010 @default.
- W4380077612 hasConceptScore W4380077612C41008148 @default.
- W4380077612 hasConceptScore W4380077612C50644808 @default.
- W4380077612 hasIssue "05" @default.
- W4380077612 hasLocation W43800776121 @default.
- W4380077612 hasOpenAccess W4380077612 @default.
- W4380077612 hasPrimaryLocation W43800776121 @default.
- W4380077612 hasRelatedWork W1583826057 @default.
- W4380077612 hasRelatedWork W2101450440 @default.
- W4380077612 hasRelatedWork W2352463596 @default.
- W4380077612 hasRelatedWork W2360099860 @default.
- W4380077612 hasRelatedWork W2376151201 @default.
- W4380077612 hasRelatedWork W2377237701 @default.
- W4380077612 hasRelatedWork W2380850119 @default.
- W4380077612 hasRelatedWork W2383675217 @default.
- W4380077612 hasRelatedWork W2393898889 @default.
- W4380077612 hasRelatedWork W4323893170 @default.
- W4380077612 hasVolume "40" @default.
- W4380077612 isParatext "false" @default.
- W4380077612 isRetracted "false" @default.
- W4380077612 workType "article" @default.