Matches in SemOpenAlex for { <https://semopenalex.org/work/W2788101503> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2788101503 abstract "Mahalanobis Metric Learning (MML) has been actively studied recently in machine learning community. Most of existing MML methods aim to learn a powerful Mahalanobis distance for computing similarity of two objects. More recently, multiple methods use matrix norm regularizers to constrain the learned distance matrixMto improve the performance. However, in real applications, the structure of the distance matrix M is complicated and cannot be characterized well by the simple matrix norm. In this paper, we propose a novel robust metric learning method with learning the structure of the distance matrix in a new and natural way. We partition M into blocks and consider each block as a random matrix variate, which is fitted by matrix variate Gaussian mixture distribution. Different from existing methods, our model has no any assumption on M and automatically learns the structure of M from the real data, where the distance matrix M often is neither sparse nor low-rank. We design an effective algorithm to optimize the proposed model and establish the corresponding theoretical guarantee. We conduct extensive evaluations on the real-world data. Experimental results show our method consistently outperforms the related state-of-the-art methods." @default.
- W2788101503 created "2018-03-06" @default.
- W2788101503 creator A5040311207 @default.
- W2788101503 creator A5060016795 @default.
- W2788101503 date "2018-04-29" @default.
- W2788101503 modified "2023-10-16" @default.
- W2788101503 title "Matrix Variate Gaussian Mixture Distribution Steered Robust Metric Learning" @default.
- W2788101503 doi "https://doi.org/10.1609/aaai.v32i1.11801" @default.
- W2788101503 hasPublicationYear "2018" @default.
- W2788101503 type Work @default.
- W2788101503 sameAs 2788101503 @default.
- W2788101503 citedByCount "4" @default.
- W2788101503 countsByYear W27881015032018 @default.
- W2788101503 countsByYear W27881015032019 @default.
- W2788101503 countsByYear W27881015032020 @default.
- W2788101503 crossrefType "journal-article" @default.
- W2788101503 hasAuthorship W2788101503A5040311207 @default.
- W2788101503 hasAuthorship W2788101503A5060016795 @default.
- W2788101503 hasBestOaLocation W27881015031 @default.
- W2788101503 hasConcept C105795698 @default.
- W2788101503 hasConcept C106487976 @default.
- W2788101503 hasConcept C111208986 @default.
- W2788101503 hasConcept C11413529 @default.
- W2788101503 hasConcept C121332964 @default.
- W2788101503 hasConcept C122123141 @default.
- W2788101503 hasConcept C141547133 @default.
- W2788101503 hasConcept C153180895 @default.
- W2788101503 hasConcept C154945302 @default.
- W2788101503 hasConcept C158693339 @default.
- W2788101503 hasConcept C159985019 @default.
- W2788101503 hasConcept C162324750 @default.
- W2788101503 hasConcept C163716315 @default.
- W2788101503 hasConcept C176217482 @default.
- W2788101503 hasConcept C1921717 @default.
- W2788101503 hasConcept C192562407 @default.
- W2788101503 hasConcept C21547014 @default.
- W2788101503 hasConcept C33923547 @default.
- W2788101503 hasConcept C41008148 @default.
- W2788101503 hasConcept C62520636 @default.
- W2788101503 hasConcept C64812099 @default.
- W2788101503 hasConcept C92207270 @default.
- W2788101503 hasConceptScore W2788101503C105795698 @default.
- W2788101503 hasConceptScore W2788101503C106487976 @default.
- W2788101503 hasConceptScore W2788101503C111208986 @default.
- W2788101503 hasConceptScore W2788101503C11413529 @default.
- W2788101503 hasConceptScore W2788101503C121332964 @default.
- W2788101503 hasConceptScore W2788101503C122123141 @default.
- W2788101503 hasConceptScore W2788101503C141547133 @default.
- W2788101503 hasConceptScore W2788101503C153180895 @default.
- W2788101503 hasConceptScore W2788101503C154945302 @default.
- W2788101503 hasConceptScore W2788101503C158693339 @default.
- W2788101503 hasConceptScore W2788101503C159985019 @default.
- W2788101503 hasConceptScore W2788101503C162324750 @default.
- W2788101503 hasConceptScore W2788101503C163716315 @default.
- W2788101503 hasConceptScore W2788101503C176217482 @default.
- W2788101503 hasConceptScore W2788101503C1921717 @default.
- W2788101503 hasConceptScore W2788101503C192562407 @default.
- W2788101503 hasConceptScore W2788101503C21547014 @default.
- W2788101503 hasConceptScore W2788101503C33923547 @default.
- W2788101503 hasConceptScore W2788101503C41008148 @default.
- W2788101503 hasConceptScore W2788101503C62520636 @default.
- W2788101503 hasConceptScore W2788101503C64812099 @default.
- W2788101503 hasConceptScore W2788101503C92207270 @default.
- W2788101503 hasIssue "1" @default.
- W2788101503 hasLocation W27881015031 @default.
- W2788101503 hasOpenAccess W2788101503 @default.
- W2788101503 hasPrimaryLocation W27881015031 @default.
- W2788101503 hasRelatedWork W1991269640 @default.
- W2788101503 hasRelatedWork W2033000528 @default.
- W2788101503 hasRelatedWork W2046875000 @default.
- W2788101503 hasRelatedWork W2097836861 @default.
- W2788101503 hasRelatedWork W2156718603 @default.
- W2788101503 hasRelatedWork W2788101503 @default.
- W2788101503 hasRelatedWork W2807748361 @default.
- W2788101503 hasRelatedWork W2891800446 @default.
- W2788101503 hasRelatedWork W3044078048 @default.
- W2788101503 hasRelatedWork W4246585671 @default.
- W2788101503 hasVolume "32" @default.
- W2788101503 isParatext "false" @default.
- W2788101503 isRetracted "false" @default.
- W2788101503 magId "2788101503" @default.
- W2788101503 workType "article" @default.