Morris et al. Future Directions in Foundations of Graph Machine Learning. ICML 2024 Zhao et al. GraphAny: A Foundation Model for Node Classification on Any Graph. Arxiv 2024. Code on Github Dong et al. Universal Link Predicto...
5. Michael Bronstein - Geometric deep learning on graphs - going beyond Euclidea是太疯狂了!来自清华大佬的压迫感!竟然把图神经网络GNN/GCN讲的如此透彻!Graph embedding/GraphSAGE/Graph Network的第54集视频,该合集共计73集,视频收藏或关注UP主,及时了解更多相
Graphconvolutional network(GCN):g_\alpha(\mathbf{f})=\alpha \tilde{\mathbf{D}}^{-1 / 2} \tilde{\mathbf{W}} \tilde{\mathbf{D}}^{-1 / 2} \mathbf{f}\tag{6}Diffusion CNN (DCNN):\mathbf{f}_{l, j}^{\mathrm{out}}=\xi\left(w_{l j} \mathbf{P}^j \mathbf{f}_l^{\mat...
Geometric deep learning on graphs and manifolds using mixture model CNNs (MoNet) [CVPR'17] 论文:https://arxiv.org/pdf/1611.08402.pdf 代码:https://github.com/sw-gong/MoNet(非官方) 1. Motivation 本文主要提出了mixture model networks (MoNet),一个将CNN架构泛化到非欧域(如graph, manifold)的通用...
Monti, Federico, et al. "Geometric deep learning on graphs and manifolds using mixture model CNNs."arXiv preprint arXiv:1611.08402(2016). 摘要:作者提出课一个统一的框架,这个框架能把传统CNN泛化到非欧空间上。作者还说以前的一些工作是他们这个工作的特例。作者在图片,图结构数据和3D形状分析上都取得了...
教程主讲人Michael Bronstein在CVPR 2017 曾发表论文《几何深度学习:在图和流形上使用CNN混合模型》Geometric deep learning on graphs and manifolds using mixture model CNNs 作者提出一个统一框架可以将CNN结构推广到非欧几里得域(图和流形)中,并可以学习局部的,平稳的,组合的特定任务特征。作者也表明了先前文献中提...
Geometric deep learning on graphs and manifolds using mixture model cnns. 2016.F. Monti, D. Boscaini, J. Masci, E. Rodola`, J. Svoboda, and M. M. Bronstein. Geometric deep learning on graphs and manifolds using mixture model CNNs. In Proceedings IEEE Conference on Computer Vision and ...
从论文Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges,了解一下几何深度学习。 https://geometricdeeplearning.com关于这个主题,研究者甚至建了一个网站。 几何深度学习——Geometric Deep Learning 几何深度学习,从对称性和不变性的角度,尝试对一大类机器学习问题进行统一。
Geometric Deep LearningGrids, Groups, Graphs, Geodesics, and GaugesMichael M. Bronstein, Joan Bruna, Taco Cohen, Petar VeličkovićRead the Proto-Book Read the Book Chapters Read the Blog Watch the Keynotes Watch the ML Street Talk Episode Follow the Lectures Contact the Authors...
Benjamin Sanchez-Lengeling et al., A Gentle Introduction to Graph Neural NetworksAmeya Daigavane et al., Understanding Convolutions on GraphsFrancesco Casalegno, Graph Convolutional Networks — Deep Learning on GraphsThomas N. Kipf, Max Welling, Semi-Supervised Classification with Graph Convolutional ...