Evaluated on CIFAR10 dataset, our method accelerates the speed of unlearning by 8. 9x for the ResNet model, and 7. 9x for the VGG model under no degradation in accuracy, compared to retraining from scratch.
Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to measure the expressiveness of graph neural networks (GNNs), showing that the neighborhood aggregation GNNs were at most as powerful as 1-WL test in distinguishing graph structures.
Ranked #2 on Graph Property Prediction on ogbg-ppa
The purpose of this paper is to provide a comprehensive survey on deep learning-based approaches in traffic prediction from multiple perspectives.
Experiment results on the challenging Kinetics dataset demonstrate that our proposed temporal modeling approaches can significantly improve existing approaches in the large-scale video recognition tasks.
Ranked #91 on Action Classification on Kinetics-400