Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382202895> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4382202895 endingPage "11425" @default.
- W4382202895 startingPage "11417" @default.
- W4382202895 abstract "Multivariate time series forecasting with hierarchical structure is widely used in real-world applications, e.g., sales predictions for the geographical hierarchy formed by cities, states, and countries. The hierarchical time series (HTS) forecasting includes two sub-tasks, i.e., forecasting and reconciliation. In the previous works, hierarchical information is only integrated in the reconciliation step to maintain coherency, but not in forecasting step for accuracy improvement. In this paper, we propose two novel tree-based feature integration mechanisms, i.e., top-down convolution and bottom-up attention to leverage the information of the hierarchical structure to improve the forecasting performance. Moreover, unlike most previous reconciliation methods which either rely on strong assumptions or focus on coherent constraints only, we utilize deep neural optimization networks, which not only achieve coherency without any assumptions, but also allow more flexible and realistic constraints to achieve task-based targets, e.g., lower under-estimation penalty and meaningful decision-making loss to facilitate the subsequent downstream tasks. Experiments on real-world datasets demonstrate that our tree-based feature integration mechanism achieves superior performances on hierarchical forecasting tasks compared to the state-of-the-art methods, and our neural optimization networks can be applied to real-world tasks effectively without any additional effort under coherence and task-based constraints." @default.
- W4382202895 created "2023-06-28" @default.
- W4382202895 creator A5021671895 @default.
- W4382202895 creator A5026486057 @default.
- W4382202895 creator A5036920814 @default.
- W4382202895 creator A5038859429 @default.
- W4382202895 creator A5039360390 @default.
- W4382202895 creator A5042259471 @default.
- W4382202895 creator A5053447705 @default.
- W4382202895 creator A5054313662 @default.
- W4382202895 creator A5056290814 @default.
- W4382202895 creator A5072815126 @default.
- W4382202895 creator A5074034944 @default.
- W4382202895 creator A5092276221 @default.
- W4382202895 date "2023-06-26" @default.
- W4382202895 modified "2023-09-22" @default.
- W4382202895 title "SLOTH: Structured Learning and Task-Based Optimization for Time Series Forecasting on Hierarchies" @default.
- W4382202895 doi "https://doi.org/10.1609/aaai.v37i9.26350" @default.
- W4382202895 hasPublicationYear "2023" @default.
- W4382202895 type Work @default.
- W4382202895 citedByCount "0" @default.
- W4382202895 crossrefType "journal-article" @default.
- W4382202895 hasAuthorship W4382202895A5021671895 @default.
- W4382202895 hasAuthorship W4382202895A5026486057 @default.
- W4382202895 hasAuthorship W4382202895A5036920814 @default.
- W4382202895 hasAuthorship W4382202895A5038859429 @default.
- W4382202895 hasAuthorship W4382202895A5039360390 @default.
- W4382202895 hasAuthorship W4382202895A5042259471 @default.
- W4382202895 hasAuthorship W4382202895A5053447705 @default.
- W4382202895 hasAuthorship W4382202895A5054313662 @default.
- W4382202895 hasAuthorship W4382202895A5056290814 @default.
- W4382202895 hasAuthorship W4382202895A5072815126 @default.
- W4382202895 hasAuthorship W4382202895A5074034944 @default.
- W4382202895 hasAuthorship W4382202895A5092276221 @default.
- W4382202895 hasBestOaLocation W43822028951 @default.
- W4382202895 hasConcept C113174947 @default.
- W4382202895 hasConcept C119857082 @default.
- W4382202895 hasConcept C124101348 @default.
- W4382202895 hasConcept C134306372 @default.
- W4382202895 hasConcept C138885662 @default.
- W4382202895 hasConcept C151406439 @default.
- W4382202895 hasConcept C153083717 @default.
- W4382202895 hasConcept C154945302 @default.
- W4382202895 hasConcept C162319229 @default.
- W4382202895 hasConcept C162324750 @default.
- W4382202895 hasConcept C163797641 @default.
- W4382202895 hasConcept C187736073 @default.
- W4382202895 hasConcept C199360897 @default.
- W4382202895 hasConcept C2776401178 @default.
- W4382202895 hasConcept C2780451532 @default.
- W4382202895 hasConcept C31170391 @default.
- W4382202895 hasConcept C33923547 @default.
- W4382202895 hasConcept C34447519 @default.
- W4382202895 hasConcept C41008148 @default.
- W4382202895 hasConcept C41895202 @default.
- W4382202895 hasConcept C50644808 @default.
- W4382202895 hasConceptScore W4382202895C113174947 @default.
- W4382202895 hasConceptScore W4382202895C119857082 @default.
- W4382202895 hasConceptScore W4382202895C124101348 @default.
- W4382202895 hasConceptScore W4382202895C134306372 @default.
- W4382202895 hasConceptScore W4382202895C138885662 @default.
- W4382202895 hasConceptScore W4382202895C151406439 @default.
- W4382202895 hasConceptScore W4382202895C153083717 @default.
- W4382202895 hasConceptScore W4382202895C154945302 @default.
- W4382202895 hasConceptScore W4382202895C162319229 @default.
- W4382202895 hasConceptScore W4382202895C162324750 @default.
- W4382202895 hasConceptScore W4382202895C163797641 @default.
- W4382202895 hasConceptScore W4382202895C187736073 @default.
- W4382202895 hasConceptScore W4382202895C199360897 @default.
- W4382202895 hasConceptScore W4382202895C2776401178 @default.
- W4382202895 hasConceptScore W4382202895C2780451532 @default.
- W4382202895 hasConceptScore W4382202895C31170391 @default.
- W4382202895 hasConceptScore W4382202895C33923547 @default.
- W4382202895 hasConceptScore W4382202895C34447519 @default.
- W4382202895 hasConceptScore W4382202895C41008148 @default.
- W4382202895 hasConceptScore W4382202895C41895202 @default.
- W4382202895 hasConceptScore W4382202895C50644808 @default.
- W4382202895 hasIssue "9" @default.
- W4382202895 hasLocation W43822028951 @default.
- W4382202895 hasOpenAccess W4382202895 @default.
- W4382202895 hasPrimaryLocation W43822028951 @default.
- W4382202895 hasRelatedWork W1514236140 @default.
- W4382202895 hasRelatedWork W1566614651 @default.
- W4382202895 hasRelatedWork W2066802334 @default.
- W4382202895 hasRelatedWork W2317605994 @default.
- W4382202895 hasRelatedWork W2358841807 @default.
- W4382202895 hasRelatedWork W4213225422 @default.
- W4382202895 hasRelatedWork W4309045103 @default.
- W4382202895 hasRelatedWork W4312937123 @default.
- W4382202895 hasRelatedWork W1629725936 @default.
- W4382202895 hasRelatedWork W2613950675 @default.
- W4382202895 hasVolume "37" @default.
- W4382202895 isParatext "false" @default.
- W4382202895 isRetracted "false" @default.
- W4382202895 workType "article" @default.