Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204669985> ?p ?o ?g. }
- W3204669985 abstract "Click-through rate prediction plays an important role in the field of recommender system and many other applications. Existing methods mainly extract user interests from user historical behaviors. However, behavioral sequences only contain users' directly interacted items, which are limited by the system's exposure, thus they are often not rich enough to reflect all the potential interests. In this paper, we propose a novel method, named Dynamic Sequential Graph Learning (DSGL), to enhance users or items' representations by utilizing collaborative information from the local sub-graphs associated with users or items. Specifically, we design the Dynamic Sequential Graph (DSG), i.e., a lightweight ego subgraph with timestamps induced from historical interactions. At every scoring moment, we construct DSGs for the target user and the candidate item respectively. Based on the DSGs, we perform graph convolutional operations iteratively in a bottom-up manner to obtain the final representations of the target user and the candidate item. As for the graph convolution, we design a Time-aware Sequential Encoding Layer that leverages the interaction time information as well as temporal dependencies to learn evolutionary user and item dynamics. Besides, we propose a Target-Preference Dual Attention Layer, composed of a preference-aware attention module and a target-aware attention module, to automatically search for parts of behaviors that are relevant to the target and alleviate the noise from unreliable neighbors. Results on real-world CTR prediction benchmarks demonstrate the improvements brought by DSGL." @default.
- W3204669985 created "2021-10-11" @default.
- W3204669985 creator A5030042334 @default.
- W3204669985 creator A5042091430 @default.
- W3204669985 creator A5081730409 @default.
- W3204669985 creator A5081897265 @default.
- W3204669985 creator A5082599714 @default.
- W3204669985 date "2021-09-26" @default.
- W3204669985 modified "2023-09-27" @default.
- W3204669985 title "Dynamic Sequential Graph Learning for Click-Through Rate Prediction." @default.
- W3204669985 cites W1924770834 @default.
- W3204669985 cites W2064675550 @default.
- W3204669985 cites W2157331557 @default.
- W3204669985 cites W2262817822 @default.
- W3204669985 cites W2475334473 @default.
- W3204669985 cites W2548570154 @default.
- W3204669985 cites W2583674722 @default.
- W3204669985 cites W2594230395 @default.
- W3204669985 cites W2624407581 @default.
- W3204669985 cites W2624431344 @default.
- W3204669985 cites W2626778328 @default.
- W3204669985 cites W2723293840 @default.
- W3204669985 cites W2766453196 @default.
- W3204669985 cites W2783272285 @default.
- W3204669985 cites W2806983170 @default.
- W3204669985 cites W2808310571 @default.
- W3204669985 cites W2908404712 @default.
- W3204669985 cites W2945944361 @default.
- W3204669985 cites W2951001079 @default.
- W3204669985 cites W2962745591 @default.
- W3204669985 cites W2962767366 @default.
- W3204669985 cites W2963493749 @default.
- W3204669985 cites W2963981376 @default.
- W3204669985 cites W2964809821 @default.
- W3204669985 cites W2997024057 @default.
- W3204669985 cites W2998313947 @default.
- W3204669985 cites W3045200674 @default.
- W3204669985 cites W3080292067 @default.
- W3204669985 cites W3094577760 @default.
- W3204669985 cites W3100278010 @default.
- W3204669985 cites W3100848837 @default.
- W3204669985 cites W3101707147 @default.
- W3204669985 cites W3167730891 @default.
- W3204669985 hasPublicationYear "2021" @default.
- W3204669985 type Work @default.
- W3204669985 sameAs 3204669985 @default.
- W3204669985 citedByCount "0" @default.
- W3204669985 crossrefType "posted-content" @default.
- W3204669985 hasAuthorship W3204669985A5030042334 @default.
- W3204669985 hasAuthorship W3204669985A5042091430 @default.
- W3204669985 hasAuthorship W3204669985A5081730409 @default.
- W3204669985 hasAuthorship W3204669985A5081897265 @default.
- W3204669985 hasAuthorship W3204669985A5082599714 @default.
- W3204669985 hasConcept C113954288 @default.
- W3204669985 hasConcept C119857082 @default.
- W3204669985 hasConcept C125411270 @default.
- W3204669985 hasConcept C132525143 @default.
- W3204669985 hasConcept C154945302 @default.
- W3204669985 hasConcept C21569690 @default.
- W3204669985 hasConcept C23123220 @default.
- W3204669985 hasConcept C2776214188 @default.
- W3204669985 hasConcept C38652104 @default.
- W3204669985 hasConcept C41008148 @default.
- W3204669985 hasConcept C557471498 @default.
- W3204669985 hasConcept C80444323 @default.
- W3204669985 hasConceptScore W3204669985C113954288 @default.
- W3204669985 hasConceptScore W3204669985C119857082 @default.
- W3204669985 hasConceptScore W3204669985C125411270 @default.
- W3204669985 hasConceptScore W3204669985C132525143 @default.
- W3204669985 hasConceptScore W3204669985C154945302 @default.
- W3204669985 hasConceptScore W3204669985C21569690 @default.
- W3204669985 hasConceptScore W3204669985C23123220 @default.
- W3204669985 hasConceptScore W3204669985C2776214188 @default.
- W3204669985 hasConceptScore W3204669985C38652104 @default.
- W3204669985 hasConceptScore W3204669985C41008148 @default.
- W3204669985 hasConceptScore W3204669985C557471498 @default.
- W3204669985 hasConceptScore W3204669985C80444323 @default.
- W3204669985 hasLocation W32046699851 @default.
- W3204669985 hasOpenAccess W3204669985 @default.
- W3204669985 hasPrimaryLocation W32046699851 @default.
- W3204669985 hasRelatedWork W2902028816 @default.
- W3204669985 hasRelatedWork W2997699135 @default.
- W3204669985 hasRelatedWork W3012705926 @default.
- W3204669985 hasRelatedWork W3051792179 @default.
- W3204669985 hasRelatedWork W3087877751 @default.
- W3204669985 hasRelatedWork W3105677627 @default.
- W3204669985 hasRelatedWork W3106433415 @default.
- W3204669985 hasRelatedWork W3106867121 @default.
- W3204669985 hasRelatedWork W3109049432 @default.
- W3204669985 hasRelatedWork W3122926833 @default.
- W3204669985 hasRelatedWork W3135856225 @default.
- W3204669985 hasRelatedWork W3145843026 @default.
- W3204669985 hasRelatedWork W3163261534 @default.
- W3204669985 hasRelatedWork W3177234138 @default.
- W3204669985 hasRelatedWork W3178564468 @default.
- W3204669985 hasRelatedWork W3192966765 @default.
- W3204669985 hasRelatedWork W3195099011 @default.
- W3204669985 hasRelatedWork W3205636893 @default.
- W3204669985 hasRelatedWork W3208387887 @default.
- W3204669985 hasRelatedWork W3209491652 @default.