Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220837072> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4220837072 endingPage "104779" @default.
- W4220837072 startingPage "104779" @default.
- W4220837072 abstract "Partial Label Learning (PLL) is a weakly supervised learning framework where each instance may be associated with more than one candidate label, among which only one is true. Traditionally, the PLL problem is solved by removing the false candidate labels based on the instance relationship, while the potentially useful information between instances and labels as well as the potential candidate label relationship is ignored. In this paper, a new PLL framework PL-CGNN is proposed, which treats the instances with false labels as noise, and the PLL is reformulated to remove the noise instances. First of all, the feature of each label class is approximately represented by the center point of all the related instances. The significant operation enables the similarity between instances and labels measurable. Next, all the candidate labels for each instance compete for the biggest similarity. To further improve the robustness of the model, the competition procedure for the most similar label is extended to the neighbors of this instance. The label with the most wins is the final ground-truth one. The relationship between candidate labels guides the situation that the competition process develops into. Through iterative competitive learning, each label class approaches the true value. Experiments carried out on diverse datasets show that the performance of the PL-CGNN model is outstanding." @default.
- W4220837072 created "2022-04-03" @default.
- W4220837072 creator A5006024361 @default.
- W4220837072 creator A5019689779 @default.
- W4220837072 creator A5047282005 @default.
- W4220837072 date "2022-05-01" @default.
- W4220837072 modified "2023-10-17" @default.
- W4220837072 title "Partial Label Learning with competitive learning graph neural network" @default.
- W4220837072 cites W1974596106 @default.
- W4220837072 cites W2005887179 @default.
- W4220837072 cites W2024328138 @default.
- W4220837072 cites W2028359993 @default.
- W4220837072 cites W2096072446 @default.
- W4220837072 cites W2106008047 @default.
- W4220837072 cites W2109606373 @default.
- W4220837072 cites W2128314196 @default.
- W4220837072 cites W2137917285 @default.
- W4220837072 cites W2237203399 @default.
- W4220837072 cites W2343569625 @default.
- W4220837072 cites W2393384312 @default.
- W4220837072 cites W2591132901 @default.
- W4220837072 cites W2592507807 @default.
- W4220837072 cites W2733555913 @default.
- W4220837072 cites W2808448059 @default.
- W4220837072 cites W2964666459 @default.
- W4220837072 cites W2981668055 @default.
- W4220837072 cites W3004782720 @default.
- W4220837072 cites W3169510026 @default.
- W4220837072 cites W4251481993 @default.
- W4220837072 doi "https://doi.org/10.1016/j.engappai.2022.104779" @default.
- W4220837072 hasPublicationYear "2022" @default.
- W4220837072 type Work @default.
- W4220837072 citedByCount "6" @default.
- W4220837072 countsByYear W42208370722022 @default.
- W4220837072 countsByYear W42208370722023 @default.
- W4220837072 crossrefType "journal-article" @default.
- W4220837072 hasAuthorship W4220837072A5006024361 @default.
- W4220837072 hasAuthorship W4220837072A5019689779 @default.
- W4220837072 hasAuthorship W4220837072A5047282005 @default.
- W4220837072 hasConcept C103278499 @default.
- W4220837072 hasConcept C104317684 @default.
- W4220837072 hasConcept C115961682 @default.
- W4220837072 hasConcept C117619785 @default.
- W4220837072 hasConcept C119857082 @default.
- W4220837072 hasConcept C138885662 @default.
- W4220837072 hasConcept C153180895 @default.
- W4220837072 hasConcept C154945302 @default.
- W4220837072 hasConcept C185592680 @default.
- W4220837072 hasConcept C2775924081 @default.
- W4220837072 hasConcept C2776401178 @default.
- W4220837072 hasConcept C41008148 @default.
- W4220837072 hasConcept C41895202 @default.
- W4220837072 hasConcept C55493867 @default.
- W4220837072 hasConcept C63479239 @default.
- W4220837072 hasConcept C99498987 @default.
- W4220837072 hasConceptScore W4220837072C103278499 @default.
- W4220837072 hasConceptScore W4220837072C104317684 @default.
- W4220837072 hasConceptScore W4220837072C115961682 @default.
- W4220837072 hasConceptScore W4220837072C117619785 @default.
- W4220837072 hasConceptScore W4220837072C119857082 @default.
- W4220837072 hasConceptScore W4220837072C138885662 @default.
- W4220837072 hasConceptScore W4220837072C153180895 @default.
- W4220837072 hasConceptScore W4220837072C154945302 @default.
- W4220837072 hasConceptScore W4220837072C185592680 @default.
- W4220837072 hasConceptScore W4220837072C2775924081 @default.
- W4220837072 hasConceptScore W4220837072C2776401178 @default.
- W4220837072 hasConceptScore W4220837072C41008148 @default.
- W4220837072 hasConceptScore W4220837072C41895202 @default.
- W4220837072 hasConceptScore W4220837072C55493867 @default.
- W4220837072 hasConceptScore W4220837072C63479239 @default.
- W4220837072 hasConceptScore W4220837072C99498987 @default.
- W4220837072 hasFunder F4320322795 @default.
- W4220837072 hasLocation W42208370721 @default.
- W4220837072 hasOpenAccess W4220837072 @default.
- W4220837072 hasPrimaryLocation W42208370721 @default.
- W4220837072 hasRelatedWork W2015538044 @default.
- W4220837072 hasRelatedWork W2016461833 @default.
- W4220837072 hasRelatedWork W2052253960 @default.
- W4220837072 hasRelatedWork W2382607599 @default.
- W4220837072 hasRelatedWork W2760085659 @default.
- W4220837072 hasRelatedWork W2970216048 @default.
- W4220837072 hasRelatedWork W3126323604 @default.
- W4220837072 hasRelatedWork W3197541072 @default.
- W4220837072 hasRelatedWork W376702462 @default.
- W4220837072 hasRelatedWork W2480412556 @default.
- W4220837072 hasVolume "111" @default.
- W4220837072 isParatext "false" @default.
- W4220837072 isRetracted "false" @default.
- W4220837072 workType "article" @default.