Matches in SemOpenAlex for { <https://semopenalex.org/work/W3080919260> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3080919260 endingPage "2920" @default.
- W3080919260 startingPage "2912" @default.
- W3080919260 abstract "Semi-supervised learning aims to learn prediction models from both labeled and unlabeled samples. There has been extensive research in this area. Among existing work, generative mixture models with Expectation-Maximization (EM) is a popular method due to clear statistical properties. However, existing literature on EM-based semi-supervised learning largely focuses on unstructured prediction, assuming that samples are independent and identically distributed. Studies on EM-based semi-supervised approach in structured prediction is limited. This article aims to fill the gap through a comparative study between unstructured and structured methods in EM-based semi-supervised learning. Specifically, we compare their theoretical properties and find that both methods can be considered as a generalization of self-training with soft class assignment of unlabeled samples, but the structured method additionally considers structural constraint in soft class assignment. We conducted a case study on real-world flood mapping datasets to compare the two methods. Results show that structured EM is more robust to class confusion caused by noise and obstacles in features in the context of the flood mapping application." @default.
- W3080919260 created "2020-09-01" @default.
- W3080919260 creator A5021681759 @default.
- W3080919260 creator A5070903469 @default.
- W3080919260 date "2022-06-01" @default.
- W3080919260 modified "2023-10-15" @default.
- W3080919260 title "Semi-Supervised Learning With the EM Algorithm: A Comparative Study Between Unstructured and Structured Prediction" @default.
- W3080919260 cites W1850843018 @default.
- W3080919260 cites W2030476695 @default.
- W3080919260 cites W2118898434 @default.
- W3080919260 cites W2125838338 @default.
- W3080919260 cites W2137450504 @default.
- W3080919260 cites W2153409933 @default.
- W3080919260 cites W2734737420 @default.
- W3080919260 cites W2809370672 @default.
- W3080919260 cites W2934379707 @default.
- W3080919260 cites W2952768605 @default.
- W3080919260 cites W2962996477 @default.
- W3080919260 cites W3036384654 @default.
- W3080919260 cites W4229511220 @default.
- W3080919260 cites W774799944 @default.
- W3080919260 doi "https://doi.org/10.1109/tkde.2020.3019038" @default.
- W3080919260 hasPublicationYear "2022" @default.
- W3080919260 type Work @default.
- W3080919260 sameAs 3080919260 @default.
- W3080919260 citedByCount "5" @default.
- W3080919260 countsByYear W30809192602021 @default.
- W3080919260 countsByYear W30809192602022 @default.
- W3080919260 crossrefType "journal-article" @default.
- W3080919260 hasAuthorship W3080919260A5021681759 @default.
- W3080919260 hasAuthorship W3080919260A5070903469 @default.
- W3080919260 hasBestOaLocation W30809192602 @default.
- W3080919260 hasConcept C105795698 @default.
- W3080919260 hasConcept C119857082 @default.
- W3080919260 hasConcept C134306372 @default.
- W3080919260 hasConcept C136389625 @default.
- W3080919260 hasConcept C151730666 @default.
- W3080919260 hasConcept C154945302 @default.
- W3080919260 hasConcept C177148314 @default.
- W3080919260 hasConcept C182081679 @default.
- W3080919260 hasConcept C22367795 @default.
- W3080919260 hasConcept C2777212361 @default.
- W3080919260 hasConcept C2779343474 @default.
- W3080919260 hasConcept C33923547 @default.
- W3080919260 hasConcept C41008148 @default.
- W3080919260 hasConcept C49781872 @default.
- W3080919260 hasConcept C50644808 @default.
- W3080919260 hasConcept C86803240 @default.
- W3080919260 hasConceptScore W3080919260C105795698 @default.
- W3080919260 hasConceptScore W3080919260C119857082 @default.
- W3080919260 hasConceptScore W3080919260C134306372 @default.
- W3080919260 hasConceptScore W3080919260C136389625 @default.
- W3080919260 hasConceptScore W3080919260C151730666 @default.
- W3080919260 hasConceptScore W3080919260C154945302 @default.
- W3080919260 hasConceptScore W3080919260C177148314 @default.
- W3080919260 hasConceptScore W3080919260C182081679 @default.
- W3080919260 hasConceptScore W3080919260C22367795 @default.
- W3080919260 hasConceptScore W3080919260C2777212361 @default.
- W3080919260 hasConceptScore W3080919260C2779343474 @default.
- W3080919260 hasConceptScore W3080919260C33923547 @default.
- W3080919260 hasConceptScore W3080919260C41008148 @default.
- W3080919260 hasConceptScore W3080919260C49781872 @default.
- W3080919260 hasConceptScore W3080919260C50644808 @default.
- W3080919260 hasConceptScore W3080919260C86803240 @default.
- W3080919260 hasFunder F4320306076 @default.
- W3080919260 hasFunder F4320308614 @default.
- W3080919260 hasIssue "6" @default.
- W3080919260 hasLocation W30809192601 @default.
- W3080919260 hasLocation W30809192602 @default.
- W3080919260 hasOpenAccess W3080919260 @default.
- W3080919260 hasPrimaryLocation W30809192601 @default.
- W3080919260 hasRelatedWork W2981850339 @default.
- W3080919260 hasRelatedWork W3046775127 @default.
- W3080919260 hasRelatedWork W3094076422 @default.
- W3080919260 hasRelatedWork W3162567751 @default.
- W3080919260 hasRelatedWork W3210156800 @default.
- W3080919260 hasRelatedWork W4220686584 @default.
- W3080919260 hasRelatedWork W4221088574 @default.
- W3080919260 hasRelatedWork W4226172683 @default.
- W3080919260 hasRelatedWork W4285260836 @default.
- W3080919260 hasRelatedWork W4319309271 @default.
- W3080919260 hasVolume "34" @default.
- W3080919260 isParatext "false" @default.
- W3080919260 isRetracted "false" @default.
- W3080919260 magId "3080919260" @default.
- W3080919260 workType "article" @default.