Matches in SemOpenAlex for { <https://semopenalex.org/work/W3123575210> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W3123575210 abstract "Achieving accurate spatio-temporal predictions in large-scale systems is extremely valuable in many real-world applications, such as weather forecasts, retail forecasting, and urban traffic forecasting. So far, most existing methods for multi-horizon, multi-task and multi-target predictions select important predicting variables via their correlations with responses, and thus it is highly possible that many forecasting models generated from those methods are not causal, leading to poor interpretability. The aim of this paper is to develop a collaborative causal spatio-temporal fusion transformer, named CausalTrans, to establish the collaborative causal effects of predictors on multiple forecasting targets, such as supply and demand in ride-sharing platforms. Specifically, we integrate the causal attention with the Conditional Average Treatment Effect (CATE) estimation method for causal inference. Moreover, we propose a novel and fast multi-head attention evolved from Taylor expansion instead of softmax, reducing time complexity from O(V2) to O(V), where V is the number of nodes in a graph. We further design a spatial graph fusion mechanism to significantly reduce the parameters' scale. We conduct a wide range of experiments to demonstrate the interpretability of causal attention, the effectiveness of various model components, and the time efficiency of our CausalTrans. As shown in these experiments, our CausalTrans framework can achieve up to 15% error reduction compared with various baseline methods." @default.
- W3123575210 created "2021-02-01" @default.
- W3123575210 creator A5007733757 @default.
- W3123575210 creator A5030705495 @default.
- W3123575210 creator A5076397911 @default.
- W3123575210 date "2021-05-04" @default.
- W3123575210 modified "2023-09-25" @default.
- W3123575210 title "Causal Probabilistic Spatio-temporal Fusion Transformers in Two-sided Ride-Hailing Markets" @default.
- W3123575210 hasPublicationYear "2021" @default.
- W3123575210 type Work @default.
- W3123575210 sameAs 3123575210 @default.
- W3123575210 citedByCount "0" @default.
- W3123575210 crossrefType "journal-article" @default.
- W3123575210 hasAuthorship W3123575210A5007733757 @default.
- W3123575210 hasAuthorship W3123575210A5030705495 @default.
- W3123575210 hasAuthorship W3123575210A5076397911 @default.
- W3123575210 hasConcept C119857082 @default.
- W3123575210 hasConcept C124101348 @default.
- W3123575210 hasConcept C149782125 @default.
- W3123575210 hasConcept C154945302 @default.
- W3123575210 hasConcept C158600405 @default.
- W3123575210 hasConcept C188441871 @default.
- W3123575210 hasConcept C2776214188 @default.
- W3123575210 hasConcept C2781067378 @default.
- W3123575210 hasConcept C33923547 @default.
- W3123575210 hasConcept C41008148 @default.
- W3123575210 hasConcept C49937458 @default.
- W3123575210 hasConcept C50644808 @default.
- W3123575210 hasConceptScore W3123575210C119857082 @default.
- W3123575210 hasConceptScore W3123575210C124101348 @default.
- W3123575210 hasConceptScore W3123575210C149782125 @default.
- W3123575210 hasConceptScore W3123575210C154945302 @default.
- W3123575210 hasConceptScore W3123575210C158600405 @default.
- W3123575210 hasConceptScore W3123575210C188441871 @default.
- W3123575210 hasConceptScore W3123575210C2776214188 @default.
- W3123575210 hasConceptScore W3123575210C2781067378 @default.
- W3123575210 hasConceptScore W3123575210C33923547 @default.
- W3123575210 hasConceptScore W3123575210C41008148 @default.
- W3123575210 hasConceptScore W3123575210C49937458 @default.
- W3123575210 hasConceptScore W3123575210C50644808 @default.
- W3123575210 hasLocation W31235752101 @default.
- W3123575210 hasOpenAccess W3123575210 @default.
- W3123575210 hasPrimaryLocation W31235752101 @default.
- W3123575210 hasRelatedWork W11849241 @default.
- W3123575210 hasRelatedWork W1651197993 @default.
- W3123575210 hasRelatedWork W2009187154 @default.
- W3123575210 hasRelatedWork W2586322860 @default.
- W3123575210 hasRelatedWork W2592539259 @default.
- W3123575210 hasRelatedWork W2798501753 @default.
- W3123575210 hasRelatedWork W2807135233 @default.
- W3123575210 hasRelatedWork W2907432055 @default.
- W3123575210 hasRelatedWork W2949468773 @default.
- W3123575210 hasRelatedWork W2952301691 @default.
- W3123575210 hasRelatedWork W2981288985 @default.
- W3123575210 hasRelatedWork W3027265310 @default.
- W3123575210 hasRelatedWork W3048645451 @default.
- W3123575210 hasRelatedWork W3082711506 @default.
- W3123575210 hasRelatedWork W3121517627 @default.
- W3123575210 hasRelatedWork W3169831079 @default.
- W3123575210 hasRelatedWork W3197099986 @default.
- W3123575210 hasRelatedWork W3201802130 @default.
- W3123575210 hasRelatedWork W3203619751 @default.
- W3123575210 hasRelatedWork W378809991 @default.
- W3123575210 isParatext "false" @default.
- W3123575210 isRetracted "false" @default.
- W3123575210 magId "3123575210" @default.
- W3123575210 workType "article" @default.