Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379137033> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4379137033 abstract "Deep graph clustering, which aims to group the nodes of a graph into disjoint clusters with deep neural networks, has achieved promising progress in recent years. However, the existing methods fail to scale to the large graph with million nodes. To solve this problem, a scalable deep graph clustering method (Dink-Net) is proposed with the idea of dilation and shrink. Firstly, by discriminating nodes, whether being corrupted by augmentations, representations are learned in a self-supervised manner. Meanwhile, the cluster centres are initialized as learnable neural parameters. Subsequently, the clustering distribution is optimized by minimizing the proposed cluster dilation loss and cluster shrink loss in an adversarial manner. By these settings, we unify the two-step clustering, i.e., representation learning and clustering optimization, into an end-to-end framework, guiding the network to learn clustering-friendly features. Besides, Dink-Net scales well to large graphs since the designed loss functions adopt the mini-batch data to optimize the clustering distribution even without performance drops. Both experimental results and theoretical analyses demonstrate the superiority of our method. Compared to the runner-up, Dink-Net achieves 9.62% NMI improvement on the ogbn-papers100M dataset with 111 million nodes and 1.6 billion edges. The source code is released at https://github.com/yueliu1999/Dink-Net. Besides, a collection (papers, codes, and datasets) of deep graph clustering is shared at https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering." @default.
- W4379137033 created "2023-06-03" @default.
- W4379137033 creator A5001937247 @default.
- W4379137033 creator A5032131582 @default.
- W4379137033 creator A5048261783 @default.
- W4379137033 creator A5056177303 @default.
- W4379137033 creator A5060693548 @default.
- W4379137033 creator A5082786719 @default.
- W4379137033 creator A5085126067 @default.
- W4379137033 date "2023-05-28" @default.
- W4379137033 modified "2023-09-27" @default.
- W4379137033 title "Dink-Net: Neural Clustering on Large Graphs" @default.
- W4379137033 doi "https://doi.org/10.48550/arxiv.2305.18405" @default.
- W4379137033 hasPublicationYear "2023" @default.
- W4379137033 type Work @default.
- W4379137033 citedByCount "0" @default.
- W4379137033 crossrefType "posted-content" @default.
- W4379137033 hasAuthorship W4379137033A5001937247 @default.
- W4379137033 hasAuthorship W4379137033A5032131582 @default.
- W4379137033 hasAuthorship W4379137033A5048261783 @default.
- W4379137033 hasAuthorship W4379137033A5056177303 @default.
- W4379137033 hasAuthorship W4379137033A5060693548 @default.
- W4379137033 hasAuthorship W4379137033A5082786719 @default.
- W4379137033 hasAuthorship W4379137033A5085126067 @default.
- W4379137033 hasBestOaLocation W43791370331 @default.
- W4379137033 hasConcept C108583219 @default.
- W4379137033 hasConcept C114614502 @default.
- W4379137033 hasConcept C124101348 @default.
- W4379137033 hasConcept C132525143 @default.
- W4379137033 hasConcept C153180895 @default.
- W4379137033 hasConcept C154945302 @default.
- W4379137033 hasConcept C22047676 @default.
- W4379137033 hasConcept C33923547 @default.
- W4379137033 hasConcept C41008148 @default.
- W4379137033 hasConcept C45340560 @default.
- W4379137033 hasConcept C48044578 @default.
- W4379137033 hasConcept C50644808 @default.
- W4379137033 hasConcept C73555534 @default.
- W4379137033 hasConcept C77088390 @default.
- W4379137033 hasConcept C80444323 @default.
- W4379137033 hasConcept C94641424 @default.
- W4379137033 hasConceptScore W4379137033C108583219 @default.
- W4379137033 hasConceptScore W4379137033C114614502 @default.
- W4379137033 hasConceptScore W4379137033C124101348 @default.
- W4379137033 hasConceptScore W4379137033C132525143 @default.
- W4379137033 hasConceptScore W4379137033C153180895 @default.
- W4379137033 hasConceptScore W4379137033C154945302 @default.
- W4379137033 hasConceptScore W4379137033C22047676 @default.
- W4379137033 hasConceptScore W4379137033C33923547 @default.
- W4379137033 hasConceptScore W4379137033C41008148 @default.
- W4379137033 hasConceptScore W4379137033C45340560 @default.
- W4379137033 hasConceptScore W4379137033C48044578 @default.
- W4379137033 hasConceptScore W4379137033C50644808 @default.
- W4379137033 hasConceptScore W4379137033C73555534 @default.
- W4379137033 hasConceptScore W4379137033C77088390 @default.
- W4379137033 hasConceptScore W4379137033C80444323 @default.
- W4379137033 hasConceptScore W4379137033C94641424 @default.
- W4379137033 hasLocation W43791370331 @default.
- W4379137033 hasLocation W43791370332 @default.
- W4379137033 hasOpenAccess W4379137033 @default.
- W4379137033 hasPrimaryLocation W43791370331 @default.
- W4379137033 hasRelatedWork W2025362236 @default.
- W4379137033 hasRelatedWork W2054781765 @default.
- W4379137033 hasRelatedWork W2155218858 @default.
- W4379137033 hasRelatedWork W2800911035 @default.
- W4379137033 hasRelatedWork W2905576882 @default.
- W4379137033 hasRelatedWork W2975827485 @default.
- W4379137033 hasRelatedWork W3153372913 @default.
- W4379137033 hasRelatedWork W3192150692 @default.
- W4379137033 hasRelatedWork W4310857077 @default.
- W4379137033 hasRelatedWork W4323896988 @default.
- W4379137033 isParatext "false" @default.
- W4379137033 isRetracted "false" @default.
- W4379137033 workType "article" @default.