FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3198339973> ?p ?o ?g. }

• W3198339973 abstract "While semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either all unlabeled examples or the unlabeled examples with a fixed high-confidence prediction during the training progress. However, it is possible that too many correct/wrong pseudo labeled examples are eliminated/selected. In this work we develop a simple yet powerful framework, whose key idea is to select a subset of training examples from the unlabeled data when performing existing SSL methods so that only the unlabeled examples with pseudo labels related to the labeled data will be used to train models. The selection is performed at each updating iteration by only keeping the examples whose losses are smaller than a given threshold that is dynamically adjusted through the iteration. Our proposed approach, Dash, enjoys its adaptivity in terms of unlabeled data selection and its theoretical guarantee. Specifically, we theoretically establish the convergence rate of Dash from the view of non-convex optimization. Finally, we empirically demonstrate the effectiveness of the proposed method in comparison with state-of-the-art over benchmarks." @default.
• W3198339973 created "2021-09-13" @default.
• W3198339973 creator A5018343158 @default.
• W3198339973 creator A5019560977 @default.
• W3198339973 creator A5030639654 @default.
• W3198339973 creator A5047734371 @default.
• W3198339973 creator A5069394608 @default.
• W3198339973 creator A5076264344 @default.
• W3198339973 creator A5084189341 @default.
• W3198339973 creator A5087131650 @default.
• W3198339973 date "2021-09-01" @default.
• W3198339973 modified "2023-09-26" @default.
• W3198339973 title "Dash: Semi-Supervised Learning with Dynamic Thresholding" @default.
• W3198339973 cites W10980763 @default.
• W3198339973 cites W1526441817 @default.
• W3198339973 cites W1532801683 @default.
• W3198339973 cites W1546148720 @default.
• W3198339973 cites W1589919686 @default.
• W3198339973 cites W1822246767 @default.
• W3198339973 cites W1975165783 @default.
• W3198339973 cites W1990334093 @default.
• W3198339973 cites W1998299325 @default.
• W3198339973 cites W2002240881 @default.
• W3198339973 cites W2019288156 @default.
• W3198339973 cites W2029463628 @default.
• W3198339973 cites W2043919728 @default.
• W3198339973 cites W2048679005 @default.
• W3198339973 cites W2049393399 @default.
• W3198339973 cites W2076063813 @default.
• W3198339973 cites W2079057609 @default.
• W3198339973 cites W2098708659 @default.
• W3198339973 cites W2101210369 @default.
• W3198339973 cites W2103024562 @default.
• W3198339973 cites W2114718442 @default.
• W3198339973 cites W2118858186 @default.
• W3198339973 cites W2126250169 @default.
• W3198339973 cites W2127499922 @default.
• W3198339973 cites W2129068307 @default.
• W3198339973 cites W2133556223 @default.
• W3198339973 cites W2136504847 @default.
• W3198339973 cites W2145494108 @default.
• W3198339973 cites W2158139315 @default.
• W3198339973 cites W2169797000 @default.
• W3198339973 cites W2170569305 @default.
• W3198339973 cites W2215421138 @default.
• W3198339973 cites W2335728318 @default.
• W3198339973 cites W2592691248 @default.
• W3198339973 cites W2604472421 @default.
• W3198339973 cites W2899748887 @default.
• W3198339973 cites W2923764619 @default.
• W3198339973 cites W2949702880 @default.
• W3198339973 cites W2949736877 @default.
• W3198339973 cites W2952204734 @default.
• W3198339973 cites W2962698540 @default.
• W3198339973 cites W2963094221 @default.
• W3198339973 cites W2963239103 @default.
• W3198339973 cites W2963263347 @default.
• W3198339973 cites W2963273221 @default.
• W3198339973 cites W2963435192 @default.
• W3198339973 cites W2963470657 @default.
• W3198339973 cites W2963614065 @default.
• W3198339973 cites W2963711681 @default.
• W3198339973 cites W2963956526 @default.
• W3198339973 cites W2964137095 @default.
• W3198339973 cites W2964159205 @default.
• W3198339973 cites W2969896498 @default.
• W3198339973 cites W2970498991 @default.
• W3198339973 cites W2970527576 @default.
• W3198339973 cites W2971120029 @default.
• W3198339973 cites W2978426779 @default.
• W3198339973 cites W2984353870 @default.
• W3198339973 cites W2996108195 @default.
• W3198339973 cites W2996501936 @default.
• W3198339973 cites W3034792991 @default.
• W3198339973 cites W3035160371 @default.
• W3198339973 cites W3035682985 @default.
• W3198339973 cites W3099570996 @default.
• W3198339973 cites W3099664505 @default.
• W3198339973 cites W3106031848 @default.
• W3198339973 cites W3118608800 @default.
• W3198339973 cites W3137695714 @default.
• W3198339973 cites W830076066 @default.
• W3198339973 cites W2530816535 @default.
• W3198339973 hasPublicationYear "2021" @default.
• W3198339973 type Work @default.
• W3198339973 sameAs 3198339973 @default.
• W3198339973 citedByCount "2" @default.
• W3198339973 countsByYear W31983399732021 @default.
• W3198339973 crossrefType "posted-content" @default.
• W3198339973 hasAuthorship W3198339973A5018343158 @default.
• W3198339973 hasAuthorship W3198339973A5019560977 @default.
• W3198339973 hasAuthorship W3198339973A5030639654 @default.
• W3198339973 hasAuthorship W3198339973A5047734371 @default.
• W3198339973 hasAuthorship W3198339973A5069394608 @default.
• W3198339973 hasAuthorship W3198339973A5076264344 @default.
• W3198339973 hasAuthorship W3198339973A5084189341 @default.
• W3198339973 hasAuthorship W3198339973A5087131650 @default.
• W3198339973 hasConcept C111919701 @default.
• W3198339973 hasConcept C115961682 @default.
• W3198339973 hasConcept C119857082 @default.

• next