Search Results for author:
Found 2 papers, 0 papers with code
MSD: Multi-Self-Distillation Learning via Multi-classifiers within Deep Neural Networks
In this paper, we propose a general training framework named multi-self-distillation learning (MSD), which mining knowledge of different classifiers within the same network and increase every classifier accuracy.
Towards Efficient Large-Scale Graph Neural Network Computing
This evolution has led to large graph-based irregular and sparse models that go beyond what existing deep learning frameworks are designed for.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
