most citedActivation Compression of Graph Neural Networks using Block-wise Quantization with Improved Variance Minimization

4 citations · 4 across the 1 of their papers we have counts for

collaborators

1 paper

stat.ML2023★ 4 cited

Activation Compression of Graph Neural Networks using Block-wise Quantization with Improved Variance Minimization

Sebastian Eliassen, Raghavendra Selvan

Efficient training of large-scale graph neural networks (GNNs) has been studied with a specific focus on reducing their memory consumption. Work by Liu et al. (2022) proposed extre…