FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3170883289> ?p ?o ?g. }

• W3170883289 abstract "Uncertainty is the only certainty there is. Modeling data uncertainty is essential for regression, especially in unconstrained settings. Traditionally the direct regression formulation is considered and the uncertainty is modeled by modifying the output space to a certain family of probabilistic distributions. On the other hand, classification based regression and ranking based solutions are more popular in practice while the direct regression methods suffer from the limited performance. How to model the uncertainty within the present-day technologies for regression remains an open issue. In this paper, we propose to learn probabilistic ordinal embeddings which represent each data as a multivariate Gaussian distribution rather than a deterministic point in the latent space. An ordinal distribution constraint is proposed to exploit the ordinal nature of regression. Our probabilistic ordinal embeddings can be integrated into popular regression approaches and empower them with the ability of uncertainty estimation. Experimental results show that our approach achieves competitive performance. Code is available at https://github.com/Li-Wanhua/POEs." @default.
• W3170883289 created "2021-06-22" @default.
• W3170883289 creator A5010357390 @default.
• W3170883289 creator A5044605985 @default.
• W3170883289 creator A5082419115 @default.
• W3170883289 creator A5084679040 @default.
• W3170883289 creator A5090079801 @default.
• W3170883289 date "2021-06-01" @default.
• W3170883289 modified "2023-10-06" @default.
• W3170883289 title "Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression" @default.
• W3170883289 cites W114375244 @default.
• W3170883289 cites W1905153633 @default.
• W3170883289 cites W1988254092 @default.
• W3170883289 cites W2009088607 @default.
• W3170883289 cites W2066454034 @default.
• W3170883289 cites W2118664399 @default.
• W3170883289 cites W2220384803 @default.
• W3170883289 cites W2440214111 @default.
• W3170883289 cites W2510725918 @default.
• W3170883289 cites W2553156677 @default.
• W3170883289 cites W2742048379 @default.
• W3170883289 cites W2748140016 @default.
• W3170883289 cites W2771116199 @default.
• W3170883289 cites W2798868324 @default.
• W3170883289 cites W2807744618 @default.
• W3170883289 cites W2807904173 @default.
• W3170883289 cites W2884490794 @default.
• W3170883289 cites W2904852565 @default.
• W3170883289 cites W2905246249 @default.
• W3170883289 cites W2949208911 @default.
• W3170883289 cites W2955216108 @default.
• W3170883289 cites W2957744218 @default.
• W3170883289 cites W2962851632 @default.
• W3170883289 cites W2963644257 @default.
• W3170883289 cites W2964339591 @default.
• W3170883289 cites W2981548364 @default.
• W3170883289 cites W2984006054 @default.
• W3170883289 cites W2986070626 @default.
• W3170883289 cites W2990759908 @default.
• W3170883289 cites W2991591391 @default.
• W3170883289 cites W3034464039 @default.
• W3170883289 cites W3034504038 @default.
• W3170883289 cites W3035376925 @default.
• W3170883289 cites W3106701815 @default.
• W3170883289 cites W4239181501 @default.
• W3170883289 cites W639708223 @default.
• W3170883289 doi "https://doi.org/10.1109/cvpr46437.2021.01368" @default.
• W3170883289 hasPublicationYear "2021" @default.
• W3170883289 type Work @default.
• W3170883289 sameAs 3170883289 @default.
• W3170883289 citedByCount "13" @default.
• W3170883289 countsByYear W31708832892021 @default.
• W3170883289 countsByYear W31708832892022 @default.
• W3170883289 countsByYear W31708832892023 @default.
• W3170883289 crossrefType "proceedings-article" @default.
• W3170883289 hasAuthorship W3170883289A5010357390 @default.
• W3170883289 hasAuthorship W3170883289A5044605985 @default.
• W3170883289 hasAuthorship W3170883289A5082419115 @default.
• W3170883289 hasAuthorship W3170883289A5084679040 @default.
• W3170883289 hasAuthorship W3170883289A5090079801 @default.
• W3170883289 hasBestOaLocation W31708832892 @default.
• W3170883289 hasConcept C105795698 @default.
• W3170883289 hasConcept C110313322 @default.
• W3170883289 hasConcept C119857082 @default.
• W3170883289 hasConcept C124101348 @default.
• W3170883289 hasConcept C152877465 @default.
• W3170883289 hasConcept C154945302 @default.
• W3170883289 hasConcept C189430467 @default.
• W3170883289 hasConcept C33923547 @default.
• W3170883289 hasConcept C41008148 @default.
• W3170883289 hasConcept C49937458 @default.
• W3170883289 hasConcept C63817138 @default.
• W3170883289 hasConcept C83546350 @default.
• W3170883289 hasConcept C85461838 @default.
• W3170883289 hasConceptScore W3170883289C105795698 @default.
• W3170883289 hasConceptScore W3170883289C110313322 @default.
• W3170883289 hasConceptScore W3170883289C119857082 @default.
• W3170883289 hasConceptScore W3170883289C124101348 @default.
• W3170883289 hasConceptScore W3170883289C152877465 @default.
• W3170883289 hasConceptScore W3170883289C154945302 @default.
• W3170883289 hasConceptScore W3170883289C189430467 @default.
• W3170883289 hasConceptScore W3170883289C33923547 @default.
• W3170883289 hasConceptScore W3170883289C41008148 @default.
• W3170883289 hasConceptScore W3170883289C49937458 @default.
• W3170883289 hasConceptScore W3170883289C63817138 @default.
• W3170883289 hasConceptScore W3170883289C83546350 @default.
• W3170883289 hasConceptScore W3170883289C85461838 @default.
• W3170883289 hasFunder F4320321001 @default.
• W3170883289 hasLocation W31708832891 @default.
• W3170883289 hasLocation W31708832892 @default.
• W3170883289 hasOpenAccess W3170883289 @default.
• W3170883289 hasPrimaryLocation W31708832891 @default.
• W3170883289 hasRelatedWork W1572610764 @default.
• W3170883289 hasRelatedWork W2050937487 @default.
• W3170883289 hasRelatedWork W2056129872 @default.
• W3170883289 hasRelatedWork W2163787596 @default.
• W3170883289 hasRelatedWork W2373197346 @default.
• W3170883289 hasRelatedWork W2902207610 @default.
• W3170883289 hasRelatedWork W2987969717 @default.
• W3170883289 hasRelatedWork W3109614413 @default.

• next