FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3028997653> ?p ?o ?g. }

• W3028997653 endingPage "1617" @default.
• W3028997653 startingPage "1603" @default.
• W3028997653 abstract "To overcome the absence of concrete supervisory signals, deep clustering models construct their own labels based on self-supervision and pseudo-supervision. However, applying these techniques can cause Feature Randomness and Feature Drift. In this paper, we formally characterize these two new concepts. On one hand, Feature Randomness takes place when a considerable portion of the pseudo-labels is deemed to be random. In this regard, the trained model can learn non-representative features. On the other hand, Feature Drift takes place when the pseudo-supervised and the reconstruction losses are jointly minimized. While penalizing the reconstruction loss aims to preserve all the inherent data information, optimizing the embedded-clustering objective drops the latent between-cluster variances. Due to this compromise, the clustering-friendly representations can be easily drifted. In this context, we propose ADEC (Adversarial Deep Embedded Clustering) a novel autoencoder-based clustering model, which relies on a discriminator network to reduce random features while avoiding the drifting effect. Our new metrics <inline-formula><tex-math notation=LaTeX>$Delta _{FR}$</tex-math></inline-formula> and <inline-formula><tex-math notation=LaTeX>$Delta _{FD}$</tex-math></inline-formula> allows to, respectively, assess the level of Feature Randomness and Feature Drift. We empirically demonstrate the suitability of our model on handling these problems using benchmark real datasets. Experimental results validate that our model outperforms state-of-the-art autoencoder-based clustering methods." @default.
• W3028997653 created "2020-06-05" @default.
• W3028997653 creator A5006211488 @default.
• W3028997653 creator A5046929101 @default.
• W3028997653 creator A5074285653 @default.
• W3028997653 date "2022-04-01" @default.
• W3028997653 modified "2023-10-16" @default.
• W3028997653 title "Adversarial Deep Embedded Clustering: On a Better Trade-off Between Feature Randomness and Feature Drift" @default.
• W3028997653 cites W1604956938 @default.
• W3028997653 cites W1644402181 @default.
• W3028997653 cites W1986007546 @default.
• W3028997653 cites W2011430131 @default.
• W3028997653 cites W2025768430 @default.
• W3028997653 cites W2053186076 @default.
• W3028997653 cites W2100659887 @default.
• W3028997653 cites W2110096996 @default.
• W3028997653 cites W2121947440 @default.
• W3028997653 cites W2129500661 @default.
• W3028997653 cites W2136635436 @default.
• W3028997653 cites W2140095548 @default.
• W3028997653 cites W2222512263 @default.
• W3028997653 cites W2321533354 @default.
• W3028997653 cites W2326925005 @default.
• W3028997653 cites W2608862709 @default.
• W3028997653 cites W2730106296 @default.
• W3028997653 cites W2741943936 @default.
• W3028997653 cites W2779692282 @default.
• W3028997653 cites W2832876791 @default.
• W3028997653 cites W2883604340 @default.
• W3028997653 cites W2883725317 @default.
• W3028997653 cites W2919115771 @default.
• W3028997653 cites W2962852342 @default.
• W3028997653 cites W2962911132 @default.
• W3028997653 cites W2963420272 @default.
• W3028997653 cites W2963840432 @default.
• W3028997653 cites W2964118618 @default.
• W3028997653 cites W2982673782 @default.
• W3028997653 cites W2990500698 @default.
• W3028997653 cites W343636949 @default.
• W3028997653 doi "https://doi.org/10.1109/tkde.2020.2997772" @default.
• W3028997653 hasPublicationYear "2022" @default.
• W3028997653 type Work @default.
• W3028997653 sameAs 3028997653 @default.
• W3028997653 citedByCount "15" @default.
• W3028997653 countsByYear W30289976532020 @default.
• W3028997653 countsByYear W30289976532021 @default.
• W3028997653 countsByYear W30289976532022 @default.
• W3028997653 countsByYear W30289976532023 @default.
• W3028997653 crossrefType "journal-article" @default.
• W3028997653 hasAuthorship W3028997653A5006211488 @default.
• W3028997653 hasAuthorship W3028997653A5046929101 @default.
• W3028997653 hasAuthorship W3028997653A5074285653 @default.
• W3028997653 hasBestOaLocation W30289976532 @default.
• W3028997653 hasConcept C101738243 @default.
• W3028997653 hasConcept C105795698 @default.
• W3028997653 hasConcept C108583219 @default.
• W3028997653 hasConcept C111442797 @default.
• W3028997653 hasConcept C11413529 @default.
• W3028997653 hasConcept C119857082 @default.
• W3028997653 hasConcept C124101348 @default.
• W3028997653 hasConcept C125112378 @default.
• W3028997653 hasConcept C13280743 @default.
• W3028997653 hasConcept C138885662 @default.
• W3028997653 hasConcept C151730666 @default.
• W3028997653 hasConcept C153180895 @default.
• W3028997653 hasConcept C154945302 @default.
• W3028997653 hasConcept C185798385 @default.
• W3028997653 hasConcept C205649164 @default.
• W3028997653 hasConcept C2776401178 @default.
• W3028997653 hasConcept C2779343474 @default.
• W3028997653 hasConcept C2779803651 @default.
• W3028997653 hasConcept C33923547 @default.
• W3028997653 hasConcept C41008148 @default.
• W3028997653 hasConcept C41895202 @default.
• W3028997653 hasConcept C73555534 @default.
• W3028997653 hasConcept C76155785 @default.
• W3028997653 hasConcept C86803240 @default.
• W3028997653 hasConcept C94915269 @default.
• W3028997653 hasConceptScore W3028997653C101738243 @default.
• W3028997653 hasConceptScore W3028997653C105795698 @default.
• W3028997653 hasConceptScore W3028997653C108583219 @default.
• W3028997653 hasConceptScore W3028997653C111442797 @default.
• W3028997653 hasConceptScore W3028997653C11413529 @default.
• W3028997653 hasConceptScore W3028997653C119857082 @default.
• W3028997653 hasConceptScore W3028997653C124101348 @default.
• W3028997653 hasConceptScore W3028997653C125112378 @default.
• W3028997653 hasConceptScore W3028997653C13280743 @default.
• W3028997653 hasConceptScore W3028997653C138885662 @default.
• W3028997653 hasConceptScore W3028997653C151730666 @default.
• W3028997653 hasConceptScore W3028997653C153180895 @default.
• W3028997653 hasConceptScore W3028997653C154945302 @default.
• W3028997653 hasConceptScore W3028997653C185798385 @default.
• W3028997653 hasConceptScore W3028997653C205649164 @default.
• W3028997653 hasConceptScore W3028997653C2776401178 @default.
• W3028997653 hasConceptScore W3028997653C2779343474 @default.
• W3028997653 hasConceptScore W3028997653C2779803651 @default.
• W3028997653 hasConceptScore W3028997653C33923547 @default.
• W3028997653 hasConceptScore W3028997653C41008148 @default.

• next