For any CSP predicate R, unweighted CSP(R) instances admit sparsifiers of size at most their non-redundancy (up to polylog factors); weighted cases are pinned to chain length, via a VC-type theorem for set families using the entropy method.
A survey on graph neural network acceleration
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
GraphLeap decouples per-layer graph construction from feature updates in Vision GNNs by using previous-layer features for the current graph, enabling pipelined FPGA acceleration with up to 95.7× CPU speedup after fine-tuning.
citing papers explorer
-
Redundancy Is All You Need (for CSP Sparsification)
For any CSP predicate R, unweighted CSP(R) instances admit sparsifiers of size at most their non-redundancy (up to polylog factors); weighted cases are pinned to chain length, via a VC-type theorem for set families using the entropy method.
-
GraphLeap: Decoupling Graph Construction and Convolution for Vision GNN Acceleration on FPGA
GraphLeap decouples per-layer graph construction from feature updates in Vision GNNs by using previous-layer features for the current graph, enabling pipelined FPGA acceleration with up to 95.7× CPU speedup after fine-tuning.