Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367147730> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4367147730 abstract "Graph Neural Networks (GNNs) are an emerging class of machine learning models which utilize structured graph information and node features to reduce high-dimensional input data to low-dimensional embeddings, from which predictions can be made. Due to the compounding effect of aggregating neighbor information, GNN inferences require raw data from many times more nodes than are targeted for prediction. Thus, on heterogeneous compute platforms, inference latency can be largely subject to the inter-device communication cost of transferring input feature data to the GPU/accelerator before computation has even begun. In this paper, we analyze the trade-off effect of pruning input features from GNN models, reducing the volume of raw data that the model works with to lower communication latency at the expense of an expected decrease in the overall model accuracy. We develop greedy and regression-based algorithms to determine which features to retain for optimal prediction accuracy. We evaluate pruned model variants and find that they can reduce inference latency by up to 80% with an accuracy loss of less than 5% compared to non-pruned models. Furthermore, we show that the latency reductions from input feature pruning can be extended under different system variables such as batch size and floating point precision." @default.
- W4367147730 created "2023-04-28" @default.
- W4367147730 creator A5015036207 @default.
- W4367147730 creator A5033166029 @default.
- W4367147730 creator A5050965079 @default.
- W4367147730 creator A5078801750 @default.
- W4367147730 date "2022-12-01" @default.
- W4367147730 modified "2023-10-14" @default.
- W4367147730 title "Input Feature Pruning for Accelerating GNN Inference on Heterogeneous Platforms" @default.
- W4367147730 doi "https://doi.org/10.1109/hipc56025.2022.00045" @default.
- W4367147730 hasPublicationYear "2022" @default.
- W4367147730 type Work @default.
- W4367147730 citedByCount "0" @default.
- W4367147730 crossrefType "proceedings-article" @default.
- W4367147730 hasAuthorship W4367147730A5015036207 @default.
- W4367147730 hasAuthorship W4367147730A5033166029 @default.
- W4367147730 hasAuthorship W4367147730A5050965079 @default.
- W4367147730 hasAuthorship W4367147730A5078801750 @default.
- W4367147730 hasConcept C108010975 @default.
- W4367147730 hasConcept C11413529 @default.
- W4367147730 hasConcept C119857082 @default.
- W4367147730 hasConcept C124101348 @default.
- W4367147730 hasConcept C132525143 @default.
- W4367147730 hasConcept C138885662 @default.
- W4367147730 hasConcept C154945302 @default.
- W4367147730 hasConcept C2776214188 @default.
- W4367147730 hasConcept C2776401178 @default.
- W4367147730 hasConcept C41008148 @default.
- W4367147730 hasConcept C41895202 @default.
- W4367147730 hasConcept C45374587 @default.
- W4367147730 hasConcept C6557445 @default.
- W4367147730 hasConcept C76155785 @default.
- W4367147730 hasConcept C80444323 @default.
- W4367147730 hasConcept C82876162 @default.
- W4367147730 hasConcept C86803240 @default.
- W4367147730 hasConceptScore W4367147730C108010975 @default.
- W4367147730 hasConceptScore W4367147730C11413529 @default.
- W4367147730 hasConceptScore W4367147730C119857082 @default.
- W4367147730 hasConceptScore W4367147730C124101348 @default.
- W4367147730 hasConceptScore W4367147730C132525143 @default.
- W4367147730 hasConceptScore W4367147730C138885662 @default.
- W4367147730 hasConceptScore W4367147730C154945302 @default.
- W4367147730 hasConceptScore W4367147730C2776214188 @default.
- W4367147730 hasConceptScore W4367147730C2776401178 @default.
- W4367147730 hasConceptScore W4367147730C41008148 @default.
- W4367147730 hasConceptScore W4367147730C41895202 @default.
- W4367147730 hasConceptScore W4367147730C45374587 @default.
- W4367147730 hasConceptScore W4367147730C6557445 @default.
- W4367147730 hasConceptScore W4367147730C76155785 @default.
- W4367147730 hasConceptScore W4367147730C80444323 @default.
- W4367147730 hasConceptScore W4367147730C82876162 @default.
- W4367147730 hasConceptScore W4367147730C86803240 @default.
- W4367147730 hasFunder F4320306076 @default.
- W4367147730 hasLocation W43671477301 @default.
- W4367147730 hasOpenAccess W4367147730 @default.
- W4367147730 hasPrimaryLocation W43671477301 @default.
- W4367147730 hasRelatedWork W2511279186 @default.
- W4367147730 hasRelatedWork W2941817504 @default.
- W4367147730 hasRelatedWork W2963058055 @default.
- W4367147730 hasRelatedWork W3125586884 @default.
- W4367147730 hasRelatedWork W3199608561 @default.
- W4367147730 hasRelatedWork W3202154562 @default.
- W4367147730 hasRelatedWork W3212328129 @default.
- W4367147730 hasRelatedWork W4320011076 @default.
- W4367147730 hasRelatedWork W4360764662 @default.
- W4367147730 hasRelatedWork W4362663447 @default.
- W4367147730 isParatext "false" @default.
- W4367147730 isRetracted "false" @default.
- W4367147730 workType "article" @default.