随笔分类 -  Spectral Graph Theory

Geometric deep learning on graphs and manifolds using mixture model CNNs
摘要：Monti, Federico, et al. "Geometric deep learning on graphs and manifolds using mixture model CNNs." arXiv preprint arXiv:1611.08402 (2016). 摘要：作者提出课一个 阅读全文
posted @ 2017-05-03 13:11 Shiyu_Huang 阅读(2222) 评论(0) 推荐(0) 编辑
Semi-Supervised Classification with Graph Convolutional Networks
摘要：Kipf, Thomas N., and Max Welling. "Semi-supervised classification with graph convolutional networks." arXiv preprint arXiv:1609.02907 (2016). 作者对Convo 阅读全文
posted @ 2017-05-02 19:58 Shiyu_Huang 阅读(2541) 评论(0) 推荐(0) 编辑
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
摘要：Defferrard, Michaël, Xavier Bresson, and Pierre Vandergheynst. "Convolutional neural networks on graphs with fast localized spectral filtering." Advan 阅读全文
posted @ 2017-05-02 14:13 Shiyu_Huang 阅读(6404) 评论(2) 推荐(0) 编辑
Spectral Graph Theory的一些定理
摘要：邻接矩阵的特征值和特征向量不会随着节点的排列不同而变化。两个图同构可以推出他们的邻接矩阵具有相同的特征值和特征向量，但是反过来不行。 阅读全文
posted @ 2017-01-04 15:09 Shiyu_Huang 阅读(581) 评论(0) 推荐(0) 编辑
图谱论(Spectral Graph Theory)基础
摘要：拉普拉斯矩阵(Laplacian matrix)，也称为导纳矩阵(Admittance matrix)或者基尔霍夫矩阵(Kirchohoff matrix) 归一化的拉普拉斯矩阵定义为 例子： 拉普拉斯矩阵性质： （1）对称半正定矩阵 （2）最小特征值为0 证明：* = (- ) * = 0 = 0 阅读全文
posted @ 2016-12-30 15:35 Shiyu_Huang 阅读(8411) 评论(1) 推荐(1) 编辑
Node Embedding
摘要：1.Kipf, Thomas N., and Max Welling. "Semi-supervised classification with graph convolutional networks." arXiv preprint arXiv:1609.02907 (2016). 2.Deff 阅读全文
posted @ 2016-12-24 15:36 Shiyu_Huang 阅读(1054) 评论(0) 推荐(0) 编辑