-
Edge-labeling Graph Neural Network for Few-shot LearningARXIV/Neural Network 2020. 4. 13. 13:44
https://arxiv.org/abs/1905.01436
Edge-labeling Graph Neural Network for Few-shot Learning
In this paper, we propose a novel edge-labeling graph neural network (EGNN), which adapts a deep neural network on the edge-labeling graph, for few-shot learning. The previous graph neural network (GNN) approaches in few-shot learning have been based on th
arxiv.org
abstract
'ARXIV > Neural Network' 카테고리의 다른 글
Matching Networks for One Shot Learning (0) 2020.04.13 Bayesian Deep Learning and a Probabilistic Perspective of Generalization (0) 2020.03.17 Two-sample Testing Using Deep Learning (0) 2020.03.11 On Feature Normalization and Data Augmentation (0) 2020.03.10 Neural Kernels Without Tangents (0) 2020.03.07