Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286909097> ?p ?o ?g. }
Showing items 1 to 56 of
56
with 100 items per page.
- W4286909097 endingPage "12" @default.
- W4286909097 startingPage "1" @default.
- W4286909097 abstract "In recent years, distributed graph convolutional networks (GCNs) training frameworks have achieved great success in learning the representation of graph-structured data with large sizes. However, existing distributed GCN training frameworks require enormous communication costs since a multitude of dependent graph data need to be transmitted from other processors. To address this issue, we propose a graph augmentation-based distributed GCN framework (GAD). In particular, GAD has two main components: GAD-Partition and GAD-Optimizer . We first propose an augmentation-based graph partition (GAD-Partition) that can divide the input graph into augmented subgraphs to reduce communication by selecting and storing as few significant vertices of other processors as possible. To further speed up distributed GCN training and improve the quality of the training result, we design a subgraph variance-based importance calculation formula and propose a novel weighted global consensus method, collectively referred to as GAD-Optimizer . This optimizer adaptively adjusts the importance of subgraphs to reduce the effect of extra variance introduced by GAD-Partition on distributed GCN training. Extensive experiments on four large-scale real-world datasets demonstrate that our framework significantly reduces the communication overhead ( ≈ 50% ), improves the convergence speed ( ≈ 2 × ) of distributed GCN training, and obtains a slight gain in accuracy ( ≈ 0.45% ) based on minimal redundancy compared to the state-of-the-art methods." @default.
- W4286909097 created "2022-07-25" @default.
- W4286909097 creator A5031266770 @default.
- W4286909097 creator A5034078186 @default.
- W4286909097 creator A5038832637 @default.
- W4286909097 creator A5058144230 @default.
- W4286909097 creator A5068123569 @default.
- W4286909097 date "2023-01-01" @default.
- W4286909097 modified "2023-09-25" @default.
- W4286909097 title "Distributed Optimization of Graph Convolutional Network Using Subgraph Variance" @default.
- W4286909097 doi "https://doi.org/10.1109/tnnls.2023.3243904" @default.
- W4286909097 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37027692" @default.
- W4286909097 hasPublicationYear "2023" @default.
- W4286909097 type Work @default.
- W4286909097 citedByCount "0" @default.
- W4286909097 crossrefType "journal-article" @default.
- W4286909097 hasAuthorship W4286909097A5031266770 @default.
- W4286909097 hasAuthorship W4286909097A5034078186 @default.
- W4286909097 hasAuthorship W4286909097A5038832637 @default.
- W4286909097 hasAuthorship W4286909097A5058144230 @default.
- W4286909097 hasAuthorship W4286909097A5068123569 @default.
- W4286909097 hasBestOaLocation W42869090972 @default.
- W4286909097 hasConcept C114614502 @default.
- W4286909097 hasConcept C132525143 @default.
- W4286909097 hasConcept C33923547 @default.
- W4286909097 hasConcept C41008148 @default.
- W4286909097 hasConcept C42812 @default.
- W4286909097 hasConcept C48903430 @default.
- W4286909097 hasConcept C80444323 @default.
- W4286909097 hasConceptScore W4286909097C114614502 @default.
- W4286909097 hasConceptScore W4286909097C132525143 @default.
- W4286909097 hasConceptScore W4286909097C33923547 @default.
- W4286909097 hasConceptScore W4286909097C41008148 @default.
- W4286909097 hasConceptScore W4286909097C42812 @default.
- W4286909097 hasConceptScore W4286909097C48903430 @default.
- W4286909097 hasConceptScore W4286909097C80444323 @default.
- W4286909097 hasLocation W42869090971 @default.
- W4286909097 hasLocation W42869090972 @default.
- W4286909097 hasLocation W42869090973 @default.
- W4286909097 hasOpenAccess W4286909097 @default.
- W4286909097 hasPrimaryLocation W42869090971 @default.
- W4286909097 hasRelatedWork W1504224153 @default.
- W4286909097 hasRelatedWork W2365526178 @default.
- W4286909097 hasRelatedWork W2390043387 @default.
- W4286909097 hasRelatedWork W2442242341 @default.
- W4286909097 hasRelatedWork W2512446543 @default.
- W4286909097 hasRelatedWork W2606672937 @default.
- W4286909097 hasRelatedWork W4244207104 @default.
- W4286909097 hasRelatedWork W4293931225 @default.
- W4286909097 hasRelatedWork W4298057244 @default.
- W4286909097 hasRelatedWork W4367189681 @default.
- W4286909097 isParatext "false" @default.
- W4286909097 isRetracted "false" @default.
- W4286909097 workType "article" @default.