PreGNN: Hardware Acceleration to Take Preprocessing Off the Critical Path in Graph Neural Networks
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Computer Architecture Letters"
DOI: 10.1109/lca.2022.3193256
Abstract: In this paper, we observe that the main performance bottleneck of emerging graph neural networks (GNNs) is not the inference algorithms themselves, but their graph data preprocessing. To take such preprocessing off the critical path… read more here.
Keywords: neural networks; take preprocessing; graph neural; critical path ... See more keywords