Matches in SemOpenAlex for { <https://semopenalex.org/work/W4365398052> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4365398052 endingPage "666" @default.
- W4365398052 startingPage "658" @default.
- W4365398052 abstract "In recent years, benefiting from the expressive power of Graph Convolutional Networks (GCNs), significant breakthroughs have been made in face clustering area. However, rare attention has been paid to GCN-based clustering on imbalanced data. Although imbalance problem has been extensively studied, the impact of imbalanced data on GCN- based linkage prediction task is quite different, which would cause problems in two aspects: imbalanced linkage labels and biased graph representations. The former is similar to that in classic image classification task, but the latter is a particular problem in GCN-based clustering via linkage prediction. Significantly biased graph representations in training can cause catastrophic over-fitting of a GCN model. To tackle these challenges, we propose a linkage-based doubly imbalanced graph learning framework for face clustering. In this framework, we evaluate the feasibility of those existing methods for imbalanced image classification problem on GCNs, and present a new method to alleviate the imbal- anced labels and also augment graph representations using a Reverse-Imbalance Weighted Sampling (RIWS) strategy. With the RIWS strategy, probability-based class balancing weights could ensure the overall distribution of positive and negative samples; In addition, weighted random sampling provides diverse subgraph structures, which effectively alleviates the over-fitting problem and improves the representation ability of GCNs. Extensive experiments on series of imbalanced benchmark datasets synthesized from MS-Celeb-1M and DeepFashion demonstrate the effectiveness and generality of our proposed method. Our implementation and the synthesized datasets will be openly available on https://github.com/espectre/GCNs_on_imbalanced_datasets.KeywordsCluster AnalysisImbalance LearningGraph Convolutional Networks" @default.
- W4365398052 created "2023-04-14" @default.
- W4365398052 creator A5023836500 @default.
- W4365398052 creator A5054957613 @default.
- W4365398052 creator A5070139134 @default.
- W4365398052 creator A5081891917 @default.
- W4365398052 creator A5088293873 @default.
- W4365398052 date "2023-01-01" @default.
- W4365398052 modified "2023-09-27" @default.
- W4365398052 title "A Linkage-based Doubly Imbalanced Graph Learning Framework for Face Clustering" @default.
- W4365398052 doi "https://doi.org/10.1137/1.9781611977653.ch74" @default.
- W4365398052 hasPublicationYear "2023" @default.
- W4365398052 type Work @default.
- W4365398052 citedByCount "0" @default.
- W4365398052 crossrefType "book-chapter" @default.
- W4365398052 hasAuthorship W4365398052A5023836500 @default.
- W4365398052 hasAuthorship W4365398052A5054957613 @default.
- W4365398052 hasAuthorship W4365398052A5070139134 @default.
- W4365398052 hasAuthorship W4365398052A5081891917 @default.
- W4365398052 hasAuthorship W4365398052A5088293873 @default.
- W4365398052 hasConcept C119857082 @default.
- W4365398052 hasConcept C124101348 @default.
- W4365398052 hasConcept C132525143 @default.
- W4365398052 hasConcept C144024400 @default.
- W4365398052 hasConcept C153180895 @default.
- W4365398052 hasConcept C154945302 @default.
- W4365398052 hasConcept C15744967 @default.
- W4365398052 hasConcept C2779304628 @default.
- W4365398052 hasConcept C2780767217 @default.
- W4365398052 hasConcept C36289849 @default.
- W4365398052 hasConcept C41008148 @default.
- W4365398052 hasConcept C542102704 @default.
- W4365398052 hasConcept C73555534 @default.
- W4365398052 hasConcept C80444323 @default.
- W4365398052 hasConceptScore W4365398052C119857082 @default.
- W4365398052 hasConceptScore W4365398052C124101348 @default.
- W4365398052 hasConceptScore W4365398052C132525143 @default.
- W4365398052 hasConceptScore W4365398052C144024400 @default.
- W4365398052 hasConceptScore W4365398052C153180895 @default.
- W4365398052 hasConceptScore W4365398052C154945302 @default.
- W4365398052 hasConceptScore W4365398052C15744967 @default.
- W4365398052 hasConceptScore W4365398052C2779304628 @default.
- W4365398052 hasConceptScore W4365398052C2780767217 @default.
- W4365398052 hasConceptScore W4365398052C36289849 @default.
- W4365398052 hasConceptScore W4365398052C41008148 @default.
- W4365398052 hasConceptScore W4365398052C542102704 @default.
- W4365398052 hasConceptScore W4365398052C73555534 @default.
- W4365398052 hasConceptScore W4365398052C80444323 @default.
- W4365398052 hasLocation W43653980521 @default.
- W4365398052 hasOpenAccess W4365398052 @default.
- W4365398052 hasPrimaryLocation W43653980521 @default.
- W4365398052 hasRelatedWork W1775397219 @default.
- W4365398052 hasRelatedWork W1969082417 @default.
- W4365398052 hasRelatedWork W2004976700 @default.
- W4365398052 hasRelatedWork W2096776307 @default.
- W4365398052 hasRelatedWork W2136485282 @default.
- W4365398052 hasRelatedWork W2347601237 @default.
- W4365398052 hasRelatedWork W2353697322 @default.
- W4365398052 hasRelatedWork W2383164569 @default.
- W4365398052 hasRelatedWork W2897995864 @default.
- W4365398052 hasRelatedWork W4205364923 @default.
- W4365398052 isParatext "false" @default.
- W4365398052 isRetracted "false" @default.
- W4365398052 workType "book-chapter" @default.