Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128590588> ?p ?o ?g. }
- W3128590588 abstract "Entity resolution targets at identifying records that represent the same real-world entity from one or more datasets. A major challenge in learning-based entity resolution is how to reduce the label cost for training. Due to the quadratic nature of record pair comparison, labeling is a costly task that often requires a significant effort from human experts. Inspired by recent advances of generative adversarial network (GAN), we propose a novel deep learning method, called ErGAN, to address the challenge. ErGAN consists of two key components: a label generator and a discriminator which are optimized alternatively through adversarial learning. To alleviate the issues of overfitting and highly imbalanced distribution, we design two novel modules for diversity and propagation, which can greatly improve the model generalization power. We have conducted extensive experiments to empirically verify the labeling and learning efficiency of ErGAN. The experimental results show that ErGAN beats the state-of-the-art baselines, including unsupervised, semi-supervised, and unsupervised learning methods." @default.
- W3128590588 created "2021-02-15" @default.
- W3128590588 creator A5044961357 @default.
- W3128590588 creator A5062784508 @default.
- W3128590588 creator A5072918717 @default.
- W3128590588 creator A5075756237 @default.
- W3128590588 date "2020-11-01" @default.
- W3128590588 modified "2023-09-24" @default.
- W3128590588 title "ERGAN: Generative Adversarial Networks for Entity Resolution" @default.
- W3128590588 cites W1134508972 @default.
- W3128590588 cites W1540007258 @default.
- W3128590588 cites W2011430131 @default.
- W3128590588 cites W2035615211 @default.
- W3128590588 cites W2182703380 @default.
- W3128590588 cites W2605181250 @default.
- W3128590588 cites W2733471169 @default.
- W3128590588 cites W2794573079 @default.
- W3128590588 cites W2798649495 @default.
- W3128590588 cites W2809134372 @default.
- W3128590588 cites W2951147191 @default.
- W3128590588 cites W2985009327 @default.
- W3128590588 cites W3003492572 @default.
- W3128590588 cites W3011807731 @default.
- W3128590588 cites W3102476541 @default.
- W3128590588 doi "https://doi.org/10.1109/icdm50108.2020.00158" @default.
- W3128590588 hasPublicationYear "2020" @default.
- W3128590588 type Work @default.
- W3128590588 sameAs 3128590588 @default.
- W3128590588 citedByCount "1" @default.
- W3128590588 countsByYear W31285905882021 @default.
- W3128590588 crossrefType "proceedings-article" @default.
- W3128590588 hasAuthorship W3128590588A5044961357 @default.
- W3128590588 hasAuthorship W3128590588A5062784508 @default.
- W3128590588 hasAuthorship W3128590588A5072918717 @default.
- W3128590588 hasAuthorship W3128590588A5075756237 @default.
- W3128590588 hasBestOaLocation W31285905882 @default.
- W3128590588 hasConcept C108583219 @default.
- W3128590588 hasConcept C119857082 @default.
- W3128590588 hasConcept C121332964 @default.
- W3128590588 hasConcept C13280743 @default.
- W3128590588 hasConcept C134306372 @default.
- W3128590588 hasConcept C154945302 @default.
- W3128590588 hasConcept C163258240 @default.
- W3128590588 hasConcept C177148314 @default.
- W3128590588 hasConcept C185798385 @default.
- W3128590588 hasConcept C205649164 @default.
- W3128590588 hasConcept C22019652 @default.
- W3128590588 hasConcept C26517878 @default.
- W3128590588 hasConcept C2779803651 @default.
- W3128590588 hasConcept C2780992000 @default.
- W3128590588 hasConcept C33923547 @default.
- W3128590588 hasConcept C37736160 @default.
- W3128590588 hasConcept C38652104 @default.
- W3128590588 hasConcept C39890363 @default.
- W3128590588 hasConcept C41008148 @default.
- W3128590588 hasConcept C50644808 @default.
- W3128590588 hasConcept C59404180 @default.
- W3128590588 hasConcept C62520636 @default.
- W3128590588 hasConcept C76155785 @default.
- W3128590588 hasConcept C8038995 @default.
- W3128590588 hasConcept C94915269 @default.
- W3128590588 hasConceptScore W3128590588C108583219 @default.
- W3128590588 hasConceptScore W3128590588C119857082 @default.
- W3128590588 hasConceptScore W3128590588C121332964 @default.
- W3128590588 hasConceptScore W3128590588C13280743 @default.
- W3128590588 hasConceptScore W3128590588C134306372 @default.
- W3128590588 hasConceptScore W3128590588C154945302 @default.
- W3128590588 hasConceptScore W3128590588C163258240 @default.
- W3128590588 hasConceptScore W3128590588C177148314 @default.
- W3128590588 hasConceptScore W3128590588C185798385 @default.
- W3128590588 hasConceptScore W3128590588C205649164 @default.
- W3128590588 hasConceptScore W3128590588C22019652 @default.
- W3128590588 hasConceptScore W3128590588C26517878 @default.
- W3128590588 hasConceptScore W3128590588C2779803651 @default.
- W3128590588 hasConceptScore W3128590588C2780992000 @default.
- W3128590588 hasConceptScore W3128590588C33923547 @default.
- W3128590588 hasConceptScore W3128590588C37736160 @default.
- W3128590588 hasConceptScore W3128590588C38652104 @default.
- W3128590588 hasConceptScore W3128590588C39890363 @default.
- W3128590588 hasConceptScore W3128590588C41008148 @default.
- W3128590588 hasConceptScore W3128590588C50644808 @default.
- W3128590588 hasConceptScore W3128590588C59404180 @default.
- W3128590588 hasConceptScore W3128590588C62520636 @default.
- W3128590588 hasConceptScore W3128590588C76155785 @default.
- W3128590588 hasConceptScore W3128590588C8038995 @default.
- W3128590588 hasConceptScore W3128590588C94915269 @default.
- W3128590588 hasFunder F4320334704 @default.
- W3128590588 hasLocation W31285905881 @default.
- W3128590588 hasLocation W31285905882 @default.
- W3128590588 hasOpenAccess W3128590588 @default.
- W3128590588 hasPrimaryLocation W31285905881 @default.
- W3128590588 hasRelatedWork W2908875379 @default.
- W3128590588 hasRelatedWork W2975432854 @default.
- W3128590588 hasRelatedWork W3082671857 @default.
- W3128590588 hasRelatedWork W3083242033 @default.
- W3128590588 hasRelatedWork W3180352537 @default.
- W3128590588 hasRelatedWork W3197610371 @default.
- W3128590588 hasRelatedWork W4221136938 @default.
- W3128590588 hasRelatedWork W4321854312 @default.
- W3128590588 hasRelatedWork W4328029048 @default.