Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312991481> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4312991481 abstract "Advances in graph neural network (GNN)-based algorithms enable machine learning on relational data. GNNs are computationally demanding since they rely upon backpropagation over the graph data that has sparse and irregular characteristics. In this paper, we propose a lightweight graph-based machine learning framework based on hyperdimensional computing (HDC) called RelHD. It maps the features of each node into a high-dimensional space and embeds relationships between nodes. Using lightweight HDC operations, RelHD enables both training and inference on graph data without backpropagation. Furthermore, we design a scalable processing in-memory (PIM) architecture based on the emerging FeFET technology to accelerate the proposed algorithm. Our strategy optimizes data allocation and operation scheduling that maximizes the accelerator performance by addressing the sparseness and irregularity of the graph. Experimental results show that RelHD offers comparable accuracy to the popular GNN-based algorithms while being up to 32× faster on GPU. Also, our FeFET-based accelerator achieves 33× of speedup and 59287× energy efficiency improvement on average over the GPU. It is 10× faster and 986× more energy efficient on average compared to the state-of-the-art in-memory processing-based GNN accelerator." @default.
- W4312991481 created "2023-01-05" @default.
- W4312991481 creator A5008291778 @default.
- W4312991481 creator A5036778557 @default.
- W4312991481 creator A5039571679 @default.
- W4312991481 creator A5053328061 @default.
- W4312991481 creator A5072579616 @default.
- W4312991481 creator A5089562358 @default.
- W4312991481 date "2022-10-01" @default.
- W4312991481 modified "2023-09-27" @default.
- W4312991481 title "RelHD: A Graph-based Learning on FeFET with Hyperdimensional Computing" @default.
- W4312991481 cites W2070862086 @default.
- W4312991481 cites W2153959628 @default.
- W4312991481 cites W2162630660 @default.
- W4312991481 cites W2168190036 @default.
- W4312991481 cites W2476008461 @default.
- W4312991481 cites W2583857261 @default.
- W4312991481 cites W2771100829 @default.
- W4312991481 cites W2791598392 @default.
- W4312991481 cites W2885334747 @default.
- W4312991481 cites W2900379535 @default.
- W4312991481 cites W2962756421 @default.
- W4312991481 cites W2963446207 @default.
- W4312991481 cites W2964811671 @default.
- W4312991481 cites W2988640543 @default.
- W4312991481 cites W3005619596 @default.
- W4312991481 cites W3098780461 @default.
- W4312991481 cites W3128387988 @default.
- W4312991481 cites W3183791462 @default.
- W4312991481 cites W3189995700 @default.
- W4312991481 cites W3198239267 @default.
- W4312991481 cites W3211445324 @default.
- W4312991481 cites W4200014673 @default.
- W4312991481 cites W4210566186 @default.
- W4312991481 cites W4212879565 @default.
- W4312991481 cites W4280579492 @default.
- W4312991481 cites W4285146458 @default.
- W4312991481 doi "https://doi.org/10.1109/iccd56317.2022.00087" @default.
- W4312991481 hasPublicationYear "2022" @default.
- W4312991481 type Work @default.
- W4312991481 citedByCount "0" @default.
- W4312991481 crossrefType "proceedings-article" @default.
- W4312991481 hasAuthorship W4312991481A5008291778 @default.
- W4312991481 hasAuthorship W4312991481A5036778557 @default.
- W4312991481 hasAuthorship W4312991481A5039571679 @default.
- W4312991481 hasAuthorship W4312991481A5053328061 @default.
- W4312991481 hasAuthorship W4312991481A5072579616 @default.
- W4312991481 hasAuthorship W4312991481A5089562358 @default.
- W4312991481 hasConcept C132525143 @default.
- W4312991481 hasConcept C154945302 @default.
- W4312991481 hasConcept C155032097 @default.
- W4312991481 hasConcept C173608175 @default.
- W4312991481 hasConcept C2776214188 @default.
- W4312991481 hasConcept C41008148 @default.
- W4312991481 hasConcept C48044578 @default.
- W4312991481 hasConcept C50644808 @default.
- W4312991481 hasConcept C68339613 @default.
- W4312991481 hasConcept C77088390 @default.
- W4312991481 hasConcept C80444323 @default.
- W4312991481 hasConceptScore W4312991481C132525143 @default.
- W4312991481 hasConceptScore W4312991481C154945302 @default.
- W4312991481 hasConceptScore W4312991481C155032097 @default.
- W4312991481 hasConceptScore W4312991481C173608175 @default.
- W4312991481 hasConceptScore W4312991481C2776214188 @default.
- W4312991481 hasConceptScore W4312991481C41008148 @default.
- W4312991481 hasConceptScore W4312991481C48044578 @default.
- W4312991481 hasConceptScore W4312991481C50644808 @default.
- W4312991481 hasConceptScore W4312991481C68339613 @default.
- W4312991481 hasConceptScore W4312991481C77088390 @default.
- W4312991481 hasConceptScore W4312991481C80444323 @default.
- W4312991481 hasLocation W43129914811 @default.
- W4312991481 hasOpenAccess W4312991481 @default.
- W4312991481 hasPrimaryLocation W43129914811 @default.
- W4312991481 hasRelatedWork W1509211761 @default.
- W4312991481 hasRelatedWork W1800827217 @default.
- W4312991481 hasRelatedWork W194688272 @default.
- W4312991481 hasRelatedWork W1967627035 @default.
- W4312991481 hasRelatedWork W2051319868 @default.
- W4312991481 hasRelatedWork W2370911386 @default.
- W4312991481 hasRelatedWork W2384714939 @default.
- W4312991481 hasRelatedWork W2499279132 @default.
- W4312991481 hasRelatedWork W2950720137 @default.
- W4312991481 hasRelatedWork W4294734199 @default.
- W4312991481 isParatext "false" @default.
- W4312991481 isRetracted "false" @default.
- W4312991481 workType "article" @default.