Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090599314> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3090599314 abstract "In online advertising systems, having a good knowledge of user behavior is crucial for click-through rate (CTR) prediction. In recent years, many researchers turn to seek a better way of user representation by modeling the behavior sequences with recurrent neural network (RNN). However, recurrent layers implicitly adopt the assumption that elements with different orders are fundamentally different, which is inefficient in many practical scenarios with much uncertainty and complicated hidden states. In this paper, we follow the paradigm of Relation Network (RN), and propose a new model called Similitude Attentive Relation Network (SARN). The user behavior is modeled as a graph, where nodes correspond to the visited items and edges correspond to the relations. To capture the latent user interest better, the model concentrates on the relations between items, rather than the translation on the time series. More specifically, the model tries to learn the similarity between items in a semantic space through a learnable dot-product operation and blend both of the item representations and relational information together as the final relations. We define our user representation on an attentive pooling of the relations directly. To verify the effectiveness of our method, extensive experiments on two public datasets and one real-world online advertising dataset are conducted. Experimental results show that our methods achieve usually better performance than others. Besides, we explore the properties of our model by controlled experiments and show the learned relational knowledge by visualizing the inner states of SARN." @default.
- W3090599314 created "2020-10-08" @default.
- W3090599314 creator A5003068779 @default.
- W3090599314 creator A5006191181 @default.
- W3090599314 creator A5080172278 @default.
- W3090599314 creator A5082066723 @default.
- W3090599314 date "2020-07-01" @default.
- W3090599314 modified "2023-10-02" @default.
- W3090599314 title "Similitude Attentive Relation Network for Click-Through Rate Prediction" @default.
- W3090599314 cites W1978609982 @default.
- W3090599314 cites W2027731328 @default.
- W3090599314 cites W2076618162 @default.
- W3090599314 cites W2474909202 @default.
- W3090599314 cites W2475334473 @default.
- W3090599314 cites W2510906045 @default.
- W3090599314 cites W2512971201 @default.
- W3090599314 cites W2548570154 @default.
- W3090599314 cites W2553905045 @default.
- W3090599314 cites W2723293840 @default.
- W3090599314 cites W2783666221 @default.
- W3090599314 cites W2793768763 @default.
- W3090599314 cites W2945623882 @default.
- W3090599314 cites W2962712142 @default.
- W3090599314 cites W2962745591 @default.
- W3090599314 cites W2964080601 @default.
- W3090599314 cites W2964105864 @default.
- W3090599314 cites W2994850640 @default.
- W3090599314 cites W3096591391 @default.
- W3090599314 doi "https://doi.org/10.1109/ijcnn48605.2020.9207521" @default.
- W3090599314 hasPublicationYear "2020" @default.
- W3090599314 type Work @default.
- W3090599314 sameAs 3090599314 @default.
- W3090599314 citedByCount "3" @default.
- W3090599314 countsByYear W30905993142021 @default.
- W3090599314 countsByYear W30905993142022 @default.
- W3090599314 countsByYear W30905993142023 @default.
- W3090599314 crossrefType "proceedings-article" @default.
- W3090599314 hasAuthorship W3090599314A5003068779 @default.
- W3090599314 hasAuthorship W3090599314A5006191181 @default.
- W3090599314 hasAuthorship W3090599314A5080172278 @default.
- W3090599314 hasAuthorship W3090599314A5082066723 @default.
- W3090599314 hasConcept C103278499 @default.
- W3090599314 hasConcept C115961682 @default.
- W3090599314 hasConcept C119857082 @default.
- W3090599314 hasConcept C124101348 @default.
- W3090599314 hasConcept C132525143 @default.
- W3090599314 hasConcept C143271835 @default.
- W3090599314 hasConcept C154945302 @default.
- W3090599314 hasConcept C17744445 @default.
- W3090599314 hasConcept C199539241 @default.
- W3090599314 hasConcept C204321447 @default.
- W3090599314 hasConcept C23123220 @default.
- W3090599314 hasConcept C2524010 @default.
- W3090599314 hasConcept C25343380 @default.
- W3090599314 hasConcept C2776359362 @default.
- W3090599314 hasConcept C32900221 @default.
- W3090599314 hasConcept C33923547 @default.
- W3090599314 hasConcept C41008148 @default.
- W3090599314 hasConcept C50644808 @default.
- W3090599314 hasConcept C70437156 @default.
- W3090599314 hasConcept C80444323 @default.
- W3090599314 hasConcept C94625758 @default.
- W3090599314 hasConceptScore W3090599314C103278499 @default.
- W3090599314 hasConceptScore W3090599314C115961682 @default.
- W3090599314 hasConceptScore W3090599314C119857082 @default.
- W3090599314 hasConceptScore W3090599314C124101348 @default.
- W3090599314 hasConceptScore W3090599314C132525143 @default.
- W3090599314 hasConceptScore W3090599314C143271835 @default.
- W3090599314 hasConceptScore W3090599314C154945302 @default.
- W3090599314 hasConceptScore W3090599314C17744445 @default.
- W3090599314 hasConceptScore W3090599314C199539241 @default.
- W3090599314 hasConceptScore W3090599314C204321447 @default.
- W3090599314 hasConceptScore W3090599314C23123220 @default.
- W3090599314 hasConceptScore W3090599314C2524010 @default.
- W3090599314 hasConceptScore W3090599314C25343380 @default.
- W3090599314 hasConceptScore W3090599314C2776359362 @default.
- W3090599314 hasConceptScore W3090599314C32900221 @default.
- W3090599314 hasConceptScore W3090599314C33923547 @default.
- W3090599314 hasConceptScore W3090599314C41008148 @default.
- W3090599314 hasConceptScore W3090599314C50644808 @default.
- W3090599314 hasConceptScore W3090599314C70437156 @default.
- W3090599314 hasConceptScore W3090599314C80444323 @default.
- W3090599314 hasConceptScore W3090599314C94625758 @default.
- W3090599314 hasLocation W30905993141 @default.
- W3090599314 hasOpenAccess W3090599314 @default.
- W3090599314 hasPrimaryLocation W30905993141 @default.
- W3090599314 hasRelatedWork W1751031993 @default.
- W3090599314 hasRelatedWork W1991536873 @default.
- W3090599314 hasRelatedWork W1998732556 @default.
- W3090599314 hasRelatedWork W2011799971 @default.
- W3090599314 hasRelatedWork W2389444300 @default.
- W3090599314 hasRelatedWork W2549162912 @default.
- W3090599314 hasRelatedWork W3093454656 @default.
- W3090599314 hasRelatedWork W3145941582 @default.
- W3090599314 hasRelatedWork W4296821948 @default.
- W3090599314 hasRelatedWork W2493102757 @default.
- W3090599314 isParatext "false" @default.
- W3090599314 isRetracted "false" @default.
- W3090599314 magId "3090599314" @default.
- W3090599314 workType "article" @default.