Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319786510> ?p ?o ?g. }
- W4319786510 endingPage "283" @default.
- W4319786510 startingPage "272" @default.
- W4319786510 abstract "Multi-Instance Multi-Label Learning (MIML) models complex objects (bags), each of which is composed with a set of instances and associated with a set of labels. Current MIML solutions still focus on a single-type of bags and assume an independent and identically distribution (IID) of training data. But these bags are linked with objects of other types, which also encode the semantics of bags. In addition, they generally need abundant labeled data for training. To effectively mine MIML objects linked with objects of other types, we propose a heterogeneous network embedding and meta learning based approach (MetaMIML). MetaMIML introduces the context learner with network embedding to learn context representations of bags for structure information extraction, the task learner to extract the meta knowledge for fast adapting to new tasks with scarce training objects, and finally fuses the structural and attribute information to predict the labels of bags/instances. In this way, MetaMIML can not only naturally deal with MIML objects at data level improving, but also exploit the power of meta-learning at the model enhancing. Experiments on benchmark datasets demonstrate that MetaMIML achieves a significantly better performance than state-of-the-art algorithms." @default.
- W4319786510 created "2023-02-11" @default.
- W4319786510 creator A5019594623 @default.
- W4319786510 creator A5026600777 @default.
- W4319786510 creator A5027082940 @default.
- W4319786510 creator A5038664632 @default.
- W4319786510 creator A5042241049 @default.
- W4319786510 creator A5066688286 @default.
- W4319786510 creator A5079800756 @default.
- W4319786510 creator A5090148962 @default.
- W4319786510 date "2023-06-01" @default.
- W4319786510 modified "2023-10-17" @default.
- W4319786510 title "Meta Multi-Instance Multi-Label learning by heterogeneous network fusion" @default.
- W4319786510 cites W1861492603 @default.
- W4319786510 cites W1938425378 @default.
- W4319786510 cites W1994860536 @default.
- W4319786510 cites W2027266161 @default.
- W4319786510 cites W2114315281 @default.
- W4319786510 cites W2118020653 @default.
- W4319786510 cites W2137917285 @default.
- W4319786510 cites W2560886373 @default.
- W4319786510 cites W2743104969 @default.
- W4319786510 cites W2808958151 @default.
- W4319786510 cites W2885692647 @default.
- W4319786510 cites W2904551296 @default.
- W4319786510 cites W2931277979 @default.
- W4319786510 cites W2945266622 @default.
- W4319786510 cites W2948164010 @default.
- W4319786510 cites W2949694084 @default.
- W4319786510 cites W2956050535 @default.
- W4319786510 cites W2964105864 @default.
- W4319786510 cites W2964983698 @default.
- W4319786510 cites W2997063620 @default.
- W4319786510 cites W3025114004 @default.
- W4319786510 cites W3034941520 @default.
- W4319786510 cites W3037117187 @default.
- W4319786510 cites W3037135716 @default.
- W4319786510 cites W3128577959 @default.
- W4319786510 cites W3153496855 @default.
- W4319786510 cites W3184957809 @default.
- W4319786510 cites W3189601601 @default.
- W4319786510 cites W3198405913 @default.
- W4319786510 cites W3213831041 @default.
- W4319786510 cites W4292722771 @default.
- W4319786510 cites W4293861233 @default.
- W4319786510 doi "https://doi.org/10.1016/j.inffus.2023.02.010" @default.
- W4319786510 hasPublicationYear "2023" @default.
- W4319786510 type Work @default.
- W4319786510 citedByCount "1" @default.
- W4319786510 crossrefType "journal-article" @default.
- W4319786510 hasAuthorship W4319786510A5019594623 @default.
- W4319786510 hasAuthorship W4319786510A5026600777 @default.
- W4319786510 hasAuthorship W4319786510A5027082940 @default.
- W4319786510 hasAuthorship W4319786510A5038664632 @default.
- W4319786510 hasAuthorship W4319786510A5042241049 @default.
- W4319786510 hasAuthorship W4319786510A5066688286 @default.
- W4319786510 hasAuthorship W4319786510A5079800756 @default.
- W4319786510 hasAuthorship W4319786510A5090148962 @default.
- W4319786510 hasBestOaLocation W43197865101 @default.
- W4319786510 hasConcept C104317684 @default.
- W4319786510 hasConcept C119857082 @default.
- W4319786510 hasConcept C124101348 @default.
- W4319786510 hasConcept C13280743 @default.
- W4319786510 hasConcept C151730666 @default.
- W4319786510 hasConcept C154945302 @default.
- W4319786510 hasConcept C162324750 @default.
- W4319786510 hasConcept C165696696 @default.
- W4319786510 hasConcept C177264268 @default.
- W4319786510 hasConcept C184337299 @default.
- W4319786510 hasConcept C185592680 @default.
- W4319786510 hasConcept C185798385 @default.
- W4319786510 hasConcept C187736073 @default.
- W4319786510 hasConcept C199360897 @default.
- W4319786510 hasConcept C205649164 @default.
- W4319786510 hasConcept C2779343474 @default.
- W4319786510 hasConcept C2780451532 @default.
- W4319786510 hasConcept C38652104 @default.
- W4319786510 hasConcept C41008148 @default.
- W4319786510 hasConcept C41608201 @default.
- W4319786510 hasConcept C55493867 @default.
- W4319786510 hasConcept C66746571 @default.
- W4319786510 hasConcept C86803240 @default.
- W4319786510 hasConceptScore W4319786510C104317684 @default.
- W4319786510 hasConceptScore W4319786510C119857082 @default.
- W4319786510 hasConceptScore W4319786510C124101348 @default.
- W4319786510 hasConceptScore W4319786510C13280743 @default.
- W4319786510 hasConceptScore W4319786510C151730666 @default.
- W4319786510 hasConceptScore W4319786510C154945302 @default.
- W4319786510 hasConceptScore W4319786510C162324750 @default.
- W4319786510 hasConceptScore W4319786510C165696696 @default.
- W4319786510 hasConceptScore W4319786510C177264268 @default.
- W4319786510 hasConceptScore W4319786510C184337299 @default.
- W4319786510 hasConceptScore W4319786510C185592680 @default.
- W4319786510 hasConceptScore W4319786510C185798385 @default.
- W4319786510 hasConceptScore W4319786510C187736073 @default.
- W4319786510 hasConceptScore W4319786510C199360897 @default.
- W4319786510 hasConceptScore W4319786510C205649164 @default.
- W4319786510 hasConceptScore W4319786510C2779343474 @default.