Matches in SemOpenAlex for { <https://semopenalex.org/work/W3004085344> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3004085344 abstract "Deep generative models (DGMs) have shown strong performance in semi-supervised learning (SSL), which incorporate discrete class information into the learning process. Yet existing methods generally overfit to the given labeled data, for only considering the conditional probability of labels. In this paper, we propose a novel discriminative regularized deep generative method for SSL, which fully exploits the discriminative and geometric information of data to address the aforementioned issue. Our method introduces the cluster and manifold assumption that maximizes the classification margin between clusters and simultaneously smooths the predictions of the data which is close in the sub-manifold of each cluster, to regularize the learning of the classifier in DGMs. To derive the regularization based on introduced assumptions, we adopt the generated data of DGMs along with labelled and unlabelled data, to model the data manifold and yield clusters based on the Gumbel-softmax distribution. Experimental results on both text and image datasets demonstrate the effectiveness and flexibility of our method, and prove that two introduced assumptions are complementary in guiding the classification boundary, thus improving the discriminative ability of the classifier." @default.
- W3004085344 created "2020-02-07" @default.
- W3004085344 creator A5018254776 @default.
- W3004085344 creator A5020612811 @default.
- W3004085344 creator A5024560014 @default.
- W3004085344 creator A5040058005 @default.
- W3004085344 creator A5076869167 @default.
- W3004085344 creator A5089527851 @default.
- W3004085344 date "2019-11-01" @default.
- W3004085344 modified "2023-10-16" @default.
- W3004085344 title "Discriminative Regularized Deep Generative Models for Semi-Supervised Learning" @default.
- W3004085344 cites W2024165284 @default.
- W3004085344 cites W2040412343 @default.
- W3004085344 cites W2053186076 @default.
- W3004085344 cites W2090891622 @default.
- W3004085344 cites W2387462954 @default.
- W3004085344 cites W2393319904 @default.
- W3004085344 cites W2469230926 @default.
- W3004085344 cites W2607500032 @default.
- W3004085344 cites W2612872092 @default.
- W3004085344 cites W2621690782 @default.
- W3004085344 cites W2783151135 @default.
- W3004085344 cites W2809156873 @default.
- W3004085344 cites W2932243578 @default.
- W3004085344 cites W2962756421 @default.
- W3004085344 cites W2963224980 @default.
- W3004085344 cites W3101413764 @default.
- W3004085344 cites W3104097132 @default.
- W3004085344 cites W3104854182 @default.
- W3004085344 doi "https://doi.org/10.1109/icdm.2019.00076" @default.
- W3004085344 hasPublicationYear "2019" @default.
- W3004085344 type Work @default.
- W3004085344 sameAs 3004085344 @default.
- W3004085344 citedByCount "2" @default.
- W3004085344 countsByYear W30040853442021 @default.
- W3004085344 countsByYear W30040853442023 @default.
- W3004085344 crossrefType "proceedings-article" @default.
- W3004085344 hasAuthorship W3004085344A5018254776 @default.
- W3004085344 hasAuthorship W3004085344A5020612811 @default.
- W3004085344 hasAuthorship W3004085344A5024560014 @default.
- W3004085344 hasAuthorship W3004085344A5040058005 @default.
- W3004085344 hasAuthorship W3004085344A5076869167 @default.
- W3004085344 hasAuthorship W3004085344A5089527851 @default.
- W3004085344 hasConcept C108583219 @default.
- W3004085344 hasConcept C119857082 @default.
- W3004085344 hasConcept C153180895 @default.
- W3004085344 hasConcept C154945302 @default.
- W3004085344 hasConcept C188441871 @default.
- W3004085344 hasConcept C22019652 @default.
- W3004085344 hasConcept C2776135515 @default.
- W3004085344 hasConcept C33923547 @default.
- W3004085344 hasConcept C39890363 @default.
- W3004085344 hasConcept C41008148 @default.
- W3004085344 hasConcept C50644808 @default.
- W3004085344 hasConcept C95623464 @default.
- W3004085344 hasConcept C97931131 @default.
- W3004085344 hasConceptScore W3004085344C108583219 @default.
- W3004085344 hasConceptScore W3004085344C119857082 @default.
- W3004085344 hasConceptScore W3004085344C153180895 @default.
- W3004085344 hasConceptScore W3004085344C154945302 @default.
- W3004085344 hasConceptScore W3004085344C188441871 @default.
- W3004085344 hasConceptScore W3004085344C22019652 @default.
- W3004085344 hasConceptScore W3004085344C2776135515 @default.
- W3004085344 hasConceptScore W3004085344C33923547 @default.
- W3004085344 hasConceptScore W3004085344C39890363 @default.
- W3004085344 hasConceptScore W3004085344C41008148 @default.
- W3004085344 hasConceptScore W3004085344C50644808 @default.
- W3004085344 hasConceptScore W3004085344C95623464 @default.
- W3004085344 hasConceptScore W3004085344C97931131 @default.
- W3004085344 hasLocation W30040853441 @default.
- W3004085344 hasOpenAccess W3004085344 @default.
- W3004085344 hasPrimaryLocation W30040853441 @default.
- W3004085344 hasRelatedWork W1530536511 @default.
- W3004085344 hasRelatedWork W2112343299 @default.
- W3004085344 hasRelatedWork W2353457699 @default.
- W3004085344 hasRelatedWork W2743258233 @default.
- W3004085344 hasRelatedWork W2766123424 @default.
- W3004085344 hasRelatedWork W2807311372 @default.
- W3004085344 hasRelatedWork W2905846897 @default.
- W3004085344 hasRelatedWork W2971416272 @default.
- W3004085344 hasRelatedWork W3099765033 @default.
- W3004085344 hasRelatedWork W4362499066 @default.
- W3004085344 isParatext "false" @default.
- W3004085344 isRetracted "false" @default.
- W3004085344 magId "3004085344" @default.
- W3004085344 workType "article" @default.