- 博客(3)
- 资源 (1)
- 收藏
- 关注
原创 最早提出“基于时空的图神经网络”论文:Learning Convolutional Neural Networks for Graphs 阅读笔记
卷积过程:将卷积过程迁移到图卷积中需要考虑两个问题:(i) Determining the node sequences for which neighborhood graphs are created;决定围绕哪些结点创建邻接图(比如上图1中的结点1-4)(ii) computing a normalization of neighborhood graphs, that is, a ...
2019-08-28 23:19:49 1315
原创 图卷积学习笔记
最早提出图网络的论文:2014-Spectral Networks and Deep Locally ConnectedNetworks on Graphs最早提出图卷积的论文:2017-Semi-Supervised Classification with Graph Convolutional Networks最早提出时空图卷积的论文:Learning Convolutional Neu...
2019-08-28 22:21:04 569
原创 [LDGCNN:Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features]论文代码阅读笔记
分类任务代码结构网络结构训练feature extractor和classifier:调用的模型是"ldgcnn"固定global feature;train函数中调用函数:save_global_feature(sess, ops, saver,layers)该函数将global feature保存在以下路径中:retrain classifier:调用的模型是"l...
2019-08-26 21:48:24 1607 1
2018-arXiv-Graph Neural Networks A Review of Methods and Applications.pdf
2019-09-21
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人