Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385565516> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4385565516 abstract "Many real-world machine learning problems involve structured prediction beyond categorical labels. However, most existing robustness certification works are devoted to the classification case. It remains open for robustness certification for more general outputs. In this paper, we propose a novel framework of robustness certification for structured prediction problems, where the output space is modeled as a semimetric space with a distance function that satisfies non-negativity and symmetry but not necessarily the triangle inequality. We further develop our tailored certification methods for binary, numerical, and hybrid inputs in structured prediction. Experiment results show that our method achieves tighter robustness guarantees than the SOTA structured certification baseline for numerical inputs (for which it only supports) with ℓ2 norm perturbation when outputs are measured by intersection over union (IoU) similarity, total variation distance, and perceptual distance. Moreover, we achieve good robustness certification for binary inputs with ℓ0 norm perturbation and hybrid inputs with corresponding perturbation when outputs are measured by Manhattan distance." @default.
- W4385565516 created "2023-08-05" @default.
- W4385565516 creator A5025153128 @default.
- W4385565516 creator A5036319627 @default.
- W4385565516 creator A5087158377 @default.
- W4385565516 date "2023-08-04" @default.
- W4385565516 modified "2023-09-27" @default.
- W4385565516 title "Robustness Certification for Structured Prediction with General Inputs via Safe Region Modeling in the Semimetric Output Space" @default.
- W4385565516 cites W1587878450 @default.
- W4385565516 cites W1834627138 @default.
- W4385565516 cites W2007339694 @default.
- W4385565516 cites W2084351206 @default.
- W4385565516 cites W2138026666 @default.
- W4385565516 cites W2419507445 @default.
- W4385565516 cites W2535410496 @default.
- W4385565516 cites W2618530766 @default.
- W4385565516 cites W2962785568 @default.
- W4385565516 cites W2963952467 @default.
- W4385565516 cites W3005588871 @default.
- W4385565516 cites W3019350928 @default.
- W4385565516 cites W3035004134 @default.
- W4385565516 cites W3047863327 @default.
- W4385565516 cites W3087838504 @default.
- W4385565516 cites W3101998545 @default.
- W4385565516 cites W3122007069 @default.
- W4385565516 cites W3124962940 @default.
- W4385565516 cites W3191453585 @default.
- W4385565516 cites W4226330442 @default.
- W4385565516 doi "https://doi.org/10.1145/3580305.3599493" @default.
- W4385565516 hasPublicationYear "2023" @default.
- W4385565516 type Work @default.
- W4385565516 citedByCount "0" @default.
- W4385565516 crossrefType "proceedings-article" @default.
- W4385565516 hasAuthorship W4385565516A5025153128 @default.
- W4385565516 hasAuthorship W4385565516A5036319627 @default.
- W4385565516 hasAuthorship W4385565516A5087158377 @default.
- W4385565516 hasBestOaLocation W43855655161 @default.
- W4385565516 hasConcept C104317684 @default.
- W4385565516 hasConcept C11413529 @default.
- W4385565516 hasConcept C126255220 @default.
- W4385565516 hasConcept C17744445 @default.
- W4385565516 hasConcept C185592680 @default.
- W4385565516 hasConcept C199539241 @default.
- W4385565516 hasConcept C33923547 @default.
- W4385565516 hasConcept C41008148 @default.
- W4385565516 hasConcept C46304622 @default.
- W4385565516 hasConcept C48372109 @default.
- W4385565516 hasConcept C55493867 @default.
- W4385565516 hasConcept C63479239 @default.
- W4385565516 hasConcept C94375191 @default.
- W4385565516 hasConceptScore W4385565516C104317684 @default.
- W4385565516 hasConceptScore W4385565516C11413529 @default.
- W4385565516 hasConceptScore W4385565516C126255220 @default.
- W4385565516 hasConceptScore W4385565516C17744445 @default.
- W4385565516 hasConceptScore W4385565516C185592680 @default.
- W4385565516 hasConceptScore W4385565516C199539241 @default.
- W4385565516 hasConceptScore W4385565516C33923547 @default.
- W4385565516 hasConceptScore W4385565516C41008148 @default.
- W4385565516 hasConceptScore W4385565516C46304622 @default.
- W4385565516 hasConceptScore W4385565516C48372109 @default.
- W4385565516 hasConceptScore W4385565516C55493867 @default.
- W4385565516 hasConceptScore W4385565516C63479239 @default.
- W4385565516 hasConceptScore W4385565516C94375191 @default.
- W4385565516 hasFunder F4320321885 @default.
- W4385565516 hasLocation W43855655161 @default.
- W4385565516 hasOpenAccess W4385565516 @default.
- W4385565516 hasPrimaryLocation W43855655161 @default.
- W4385565516 hasRelatedWork W1997381757 @default.
- W4385565516 hasRelatedWork W2081388382 @default.
- W4385565516 hasRelatedWork W2386767533 @default.
- W4385565516 hasRelatedWork W3119917739 @default.
- W4385565516 hasRelatedWork W3127470697 @default.
- W4385565516 hasRelatedWork W3204597924 @default.
- W4385565516 hasRelatedWork W4312269540 @default.
- W4385565516 hasRelatedWork W4320724748 @default.
- W4385565516 hasRelatedWork W4362509612 @default.
- W4385565516 hasRelatedWork W4379087257 @default.
- W4385565516 isParatext "false" @default.
- W4385565516 isRetracted "false" @default.
- W4385565516 workType "article" @default.