graph neural network
文章平均质量分 77
LUQC638
这个作者很懒,什么都没留下…
展开
-
Pytorch-geomretic学习笔记 params_count,sparseTensor
params_count(model),model是nn.Module类型的,计算参数的数量。SparseTensor:rom torch_sparse import SparseTensoradj = SparseTensor(row=edge_index[0], col=edge_index[1], value=..., sparse_sizes=(num_nodes, num_nodes))# value is optional and can b原创 2022-04-12 10:10:19 · 1564 阅读 · 0 评论 -
SELF-TRAINING OF GRAPH NEURAL NETWORKS USING SIMILARITY REFERENCE
作者认为传统的方法只使用了被采样出来的认为是clean的data进行训练,那些没有被sample的数据就没有被利用起来。作者提出了一个基于图的学习框架使得网络能够传播被sample的数据的标签信息到临近的数据(无论是被采样还是没有被采样出来的)。作者提出的self-training的策略利用没有标签也没有被sample的数据,通过使用采样的数据的信息来正则化网络的更新。Introductiondecoupling method认为被两个网络预测为不同的结果的数据反而更有价值。mentornet使用了原创 2022-03-25 10:17:04 · 1286 阅读 · 0 评论 -
learning to reweight examples for robust deep learning
deep neural networks can easily overfit to training biases and label noises. In addition to various regularizers, example reweighting algorithms are popular solutions.They propose a novel meta-learning algorithm that learns to assign weights to training原创 2022-03-21 22:47:33 · 695 阅读 · 0 评论 -
CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning 解读
Noisy label learning, semi-supervised learning, and contrastive learning are three different strategies for designing learning processes requiring less annotation cost.原创 2022-03-14 21:58:58 · 1360 阅读 · 0 评论 -
torch_geometric 入门,加载benchmark数据集
来自官网的例子:from torch.nn import Linear, ReLU# from torch_geometric.nn import Sequential, GCNConvimport torchfrom torch_geometric.datasets import Planetoid, TUDatasetfrom torch_scatter import scatter_meanfrom torch_geometric.loader import DataLoader原创 2022-03-11 22:40:29 · 708 阅读 · 0 评论 -
torch-geometric 大坑(2) conda 和pip安装
自己的Python是conda环境下面的,pip安装后,表明没问题,一运行就报错,还是得用conda的命令,来自pyg官网:https://pytorch-geometric.readthedocs.io/en/latest/notes/installation.htmlhttps://pytorch-geometric.readthedocs.io/en/latest/notes/installation.html结果自己一直用的是pip命令:问题的来源承接上一次安装好torch geo.原创 2022-03-09 23:24:27 · 1577 阅读 · 0 评论