Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385654316> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4385654316 endingPage "123" @default.
- W4385654316 startingPage "114" @default.
- W4385654316 abstract "Graph neural networks (GNN) have shown great application potential in scientific research applications, biomedicine, and other fields, which exhibit superior feature representation capabilities for graph data with non-Euclidean structures. These capabilities are enabled efficiently by sparse matrix-matrix multiplication (SPMM) and sparse matrix-vector multiplication (SPMV) that operate on sparse matrix representations of graph structures. However, SpMM has the characteristics of high memory occupation and irregular memory access, which leads to low storage and computational efficiency. To address the above issues, this paper proposes a sparse matrix optimization method, including a sparse matrix format and a performance model. The format, namely BMCOO, divides the sparse matrix into multiple blocks and adopts the bitmap to compress the position information of non-zero elements in each block. This paper further designs an SpMV algorithm in BMCOO format on GPU. In addition, a multi-channel SpMV performance model is constructed to predict the execution time of SpMV by combining the sparse matrix scale and system architecture parameters. Then the performance model fine-tunes the graph partitioning of the GNN training process. Experiments on the SuiteSparse and the Open Graph Benchmark datasets verify the effectiveness and superiority of the proposed method." @default.
- W4385654316 created "2023-08-09" @default.
- W4385654316 creator A5001703908 @default.
- W4385654316 creator A5006958929 @default.
- W4385654316 creator A5031941017 @default.
- W4385654316 creator A5037237122 @default.
- W4385654316 creator A5040192354 @default.
- W4385654316 creator A5064888675 @default.
- W4385654316 creator A5073200513 @default.
- W4385654316 creator A5089707199 @default.
- W4385654316 date "2023-01-01" @default.
- W4385654316 modified "2023-10-16" @default.
- W4385654316 title "A Sparse Matrix Optimization Method for Graph Neural Networks Training" @default.
- W4385654316 cites W2009654791 @default.
- W4385654316 cites W2070232376 @default.
- W4385654316 cites W2089908605 @default.
- W4385654316 cites W2130289795 @default.
- W4385654316 cites W2788264912 @default.
- W4385654316 cites W3132695675 @default.
- W4385654316 cites W3198756702 @default.
- W4385654316 cites W4210257598 @default.
- W4385654316 cites W4247712932 @default.
- W4385654316 cites W4247828381 @default.
- W4385654316 cites W4298009069 @default.
- W4385654316 doi "https://doi.org/10.1007/978-3-031-40283-8_11" @default.
- W4385654316 hasPublicationYear "2023" @default.
- W4385654316 type Work @default.
- W4385654316 citedByCount "0" @default.
- W4385654316 crossrefType "book-chapter" @default.
- W4385654316 hasAuthorship W4385654316A5001703908 @default.
- W4385654316 hasAuthorship W4385654316A5006958929 @default.
- W4385654316 hasAuthorship W4385654316A5031941017 @default.
- W4385654316 hasAuthorship W4385654316A5037237122 @default.
- W4385654316 hasAuthorship W4385654316A5040192354 @default.
- W4385654316 hasAuthorship W4385654316A5064888675 @default.
- W4385654316 hasAuthorship W4385654316A5073200513 @default.
- W4385654316 hasAuthorship W4385654316A5089707199 @default.
- W4385654316 hasConcept C102192266 @default.
- W4385654316 hasConcept C106487976 @default.
- W4385654316 hasConcept C11413529 @default.
- W4385654316 hasConcept C121332964 @default.
- W4385654316 hasConcept C124066611 @default.
- W4385654316 hasConcept C13251829 @default.
- W4385654316 hasConcept C132525143 @default.
- W4385654316 hasConcept C154945302 @default.
- W4385654316 hasConcept C159985019 @default.
- W4385654316 hasConcept C163716315 @default.
- W4385654316 hasConcept C17349429 @default.
- W4385654316 hasConcept C173608175 @default.
- W4385654316 hasConcept C192562407 @default.
- W4385654316 hasConcept C203776342 @default.
- W4385654316 hasConcept C3115412 @default.
- W4385654316 hasConcept C41008148 @default.
- W4385654316 hasConcept C56372850 @default.
- W4385654316 hasConcept C62520636 @default.
- W4385654316 hasConcept C80444323 @default.
- W4385654316 hasConcept C84114770 @default.
- W4385654316 hasConceptScore W4385654316C102192266 @default.
- W4385654316 hasConceptScore W4385654316C106487976 @default.
- W4385654316 hasConceptScore W4385654316C11413529 @default.
- W4385654316 hasConceptScore W4385654316C121332964 @default.
- W4385654316 hasConceptScore W4385654316C124066611 @default.
- W4385654316 hasConceptScore W4385654316C13251829 @default.
- W4385654316 hasConceptScore W4385654316C132525143 @default.
- W4385654316 hasConceptScore W4385654316C154945302 @default.
- W4385654316 hasConceptScore W4385654316C159985019 @default.
- W4385654316 hasConceptScore W4385654316C163716315 @default.
- W4385654316 hasConceptScore W4385654316C17349429 @default.
- W4385654316 hasConceptScore W4385654316C173608175 @default.
- W4385654316 hasConceptScore W4385654316C192562407 @default.
- W4385654316 hasConceptScore W4385654316C203776342 @default.
- W4385654316 hasConceptScore W4385654316C3115412 @default.
- W4385654316 hasConceptScore W4385654316C41008148 @default.
- W4385654316 hasConceptScore W4385654316C56372850 @default.
- W4385654316 hasConceptScore W4385654316C62520636 @default.
- W4385654316 hasConceptScore W4385654316C80444323 @default.
- W4385654316 hasConceptScore W4385654316C84114770 @default.
- W4385654316 hasLocation W43856543161 @default.
- W4385654316 hasOpenAccess W4385654316 @default.
- W4385654316 hasPrimaryLocation W43856543161 @default.
- W4385654316 hasRelatedWork W1543798151 @default.
- W4385654316 hasRelatedWork W1832263773 @default.
- W4385654316 hasRelatedWork W1948183148 @default.
- W4385654316 hasRelatedWork W1991173951 @default.
- W4385654316 hasRelatedWork W2014256025 @default.
- W4385654316 hasRelatedWork W2042960494 @default.
- W4385654316 hasRelatedWork W2542063421 @default.
- W4385654316 hasRelatedWork W2582955817 @default.
- W4385654316 hasRelatedWork W2898875679 @default.
- W4385654316 hasRelatedWork W4316252382 @default.
- W4385654316 isParatext "false" @default.
- W4385654316 isRetracted "false" @default.
- W4385654316 workType "book-chapter" @default.