Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384919605> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4384919605 abstract "Deep learning (DL) approaches are being increasingly used for time-series forecasting, with many efforts devoted to designing complex DL models. Recent studies have shown that the DL success is often attributed to effective data representations, fostering the fields of feature engineering and representation learning. However, automated approaches for feature learning are typically limited with respect to incorporating prior knowledge, identifying interactions among variables, and choosing evaluation metrics to ensure that the models are reliable. To improve on these limitations, this paper contributes a novel visual analytics framework, namely TimeTuner, designed to help analysts understand how model behaviors are associated with localized correlations, stationarity, and granularity of time-series representations. The system mainly consists of the following two-stage technique: We first leverage counterfactual explanations to connect the relationships among time-series representations, multivariate features and model predictions. Next, we design multiple coordinated views including a partition-based correlation matrix and juxtaposed bivariate stripes, and provide a set of interactions that allow users to step into the transformation selection process, navigate through the feature space, and reason the model performance. We instantiate TimeTuner with two transformation methods of smoothing and sampling, and demonstrate its applicability on real-world time-series forecasting of univariate sunspots and multivariate air pollutants. Feedback from domain experts indicates that our system can help characterize time-series representations and guide the feature engineering processes." @default.
- W4384919605 created "2023-07-21" @default.
- W4384919605 creator A5013075379 @default.
- W4384919605 creator A5061698636 @default.
- W4384919605 creator A5071718252 @default.
- W4384919605 creator A5086643675 @default.
- W4384919605 date "2023-07-19" @default.
- W4384919605 modified "2023-09-24" @default.
- W4384919605 title "TimeTuner: Diagnosing Time Representations for Time-Series Forecasting with Counterfactual Explanations" @default.
- W4384919605 doi "https://doi.org/10.48550/arxiv.2307.09916" @default.
- W4384919605 hasPublicationYear "2023" @default.
- W4384919605 type Work @default.
- W4384919605 citedByCount "0" @default.
- W4384919605 crossrefType "posted-content" @default.
- W4384919605 hasAuthorship W4384919605A5013075379 @default.
- W4384919605 hasAuthorship W4384919605A5061698636 @default.
- W4384919605 hasAuthorship W4384919605A5071718252 @default.
- W4384919605 hasAuthorship W4384919605A5086643675 @default.
- W4384919605 hasBestOaLocation W43849196051 @default.
- W4384919605 hasConcept C108650721 @default.
- W4384919605 hasConcept C111472728 @default.
- W4384919605 hasConcept C119857082 @default.
- W4384919605 hasConcept C124101348 @default.
- W4384919605 hasConcept C138885662 @default.
- W4384919605 hasConcept C151406439 @default.
- W4384919605 hasConcept C153083717 @default.
- W4384919605 hasConcept C154945302 @default.
- W4384919605 hasConcept C161584116 @default.
- W4384919605 hasConcept C199163554 @default.
- W4384919605 hasConcept C2776401178 @default.
- W4384919605 hasConcept C31972630 @default.
- W4384919605 hasConcept C3770464 @default.
- W4384919605 hasConcept C41008148 @default.
- W4384919605 hasConcept C41895202 @default.
- W4384919605 hasConcept C64341305 @default.
- W4384919605 hasConceptScore W4384919605C108650721 @default.
- W4384919605 hasConceptScore W4384919605C111472728 @default.
- W4384919605 hasConceptScore W4384919605C119857082 @default.
- W4384919605 hasConceptScore W4384919605C124101348 @default.
- W4384919605 hasConceptScore W4384919605C138885662 @default.
- W4384919605 hasConceptScore W4384919605C151406439 @default.
- W4384919605 hasConceptScore W4384919605C153083717 @default.
- W4384919605 hasConceptScore W4384919605C154945302 @default.
- W4384919605 hasConceptScore W4384919605C161584116 @default.
- W4384919605 hasConceptScore W4384919605C199163554 @default.
- W4384919605 hasConceptScore W4384919605C2776401178 @default.
- W4384919605 hasConceptScore W4384919605C31972630 @default.
- W4384919605 hasConceptScore W4384919605C3770464 @default.
- W4384919605 hasConceptScore W4384919605C41008148 @default.
- W4384919605 hasConceptScore W4384919605C41895202 @default.
- W4384919605 hasConceptScore W4384919605C64341305 @default.
- W4384919605 hasLocation W43849196051 @default.
- W4384919605 hasOpenAccess W4384919605 @default.
- W4384919605 hasPrimaryLocation W43849196051 @default.
- W4384919605 hasRelatedWork W1994909720 @default.
- W4384919605 hasRelatedWork W2096128876 @default.
- W4384919605 hasRelatedWork W2177839369 @default.
- W4384919605 hasRelatedWork W2354804553 @default.
- W4384919605 hasRelatedWork W2508420332 @default.
- W4384919605 hasRelatedWork W260797790 @default.
- W4384919605 hasRelatedWork W3005618458 @default.
- W4384919605 hasRelatedWork W3121642497 @default.
- W4384919605 hasRelatedWork W314466983 @default.
- W4384919605 hasRelatedWork W2183901182 @default.
- W4384919605 isParatext "false" @default.
- W4384919605 isRetracted "false" @default.
- W4384919605 workType "article" @default.