可以得出,该池化不是仅对节点进行删除操作,而是对graph进行了聚类,类间的邻接矩阵和特征矩阵全都改变了。但是此模型却优于谱聚类,因为谱聚类仅仅考虑了邻接矩阵,而该框架通过引入了 GNN 同时考虑了邻接矩阵和特征矩阵。且不需要进行谱分解,降低了计算复杂度。在图池化过程中类似于谱聚类是一种无监督的训练,也就是...
Graph Clustering with Graph Neural NetworksTsitsulin, AntonPalowitch, JohnPerozzi, BryanMüller, EmmanuelJournal of Machine Learning Research
Zhang和Chen[36,36]认为仅从节点对的局部邻居计算连接似然是足够的,并提出了一个Weisfeiler-Lehman Neural Machine [35] 和一个graph neural network [36]来从局部子图学习一般图结构特征。这与我们的工作密切相关,因为聚类任务可以简化为连接预测问题,我们也能利用图神经网络来从局部图进行学习。 Graph convolutional ...
et al. Cell clustering for spatial transcriptomics data with graph neural networks. Nat Comput Sci 2, 399–408 (2022). https://doi.org/10.1038/s43588-022-00266-5 Download citation Received18 October 2021 Accepted19 May 2022 Published27 June 2022 Issue DateJune 2022 DOIhttps://doi.org/...
Cell clustering for spatial transcriptomics data with graph neural networks Nat Comput Sci, 2 (2022), pp. 399-408, 10.1038/s43588-022-00266-5 View in ScopusGoogle Scholar [30] Y. Zong, T. Yu, X. Wang, Y. Wang, Z. Hu, Y. Li conST: an interpretable multi-modal contrastive learning...
Cell clustering for spatial transcriptomics data with graph neural networks Article27 June 2022 Introduction Within the tissues of multicellular organisms, cells are organized into groups of similar cells physically clustered together. Linking gene expression of cells with their spatial distribution is crucia...
我们提出了一个层次图神经网络(GNN)模型,该模型学习如何使用一组图像训练集,将一组图像聚类成未知数量的身份,该训练集使用属于不相交身份集的标签进行注释。我们的分层 GNN 使用一种新颖的方法来合并在层次结构的每个级别预测的连接组件,以在下一个级别形成一个新图。与完全无监督的层次聚类不同,分组和复杂性标准的...
In this paper, we propose a novel Multi-View Attribute GraphConvolution Networks for Clustering (MAGCN), a general method to multi-view graph neural network. (提出了什么) MAGCN is designed with dual encoders that reconstruct the extracted features in high dimensions and integrate the low dimensi...
基于GNN的层次人脸聚类-Learning Hierarchical Graph Neural Networks for Image Clustering 一、简介 本次介绍的文章来自CVPR 2021,是目前图像聚类领域比较新的一篇文章,作者来自亚马逊aws。 本文提出了一种有监督的层次GNN模型,使用一种新方法融合每一层的的连接分量,从而在下一层形成新的图。对比sota F-score平均...
However, most existing multi-view graph based methods perform clustering on the fixed input graphs, and the results are dependent on the quality of input graphs. In this paper, instead of fixing the input graphs, we propose Multi-view clustering with Adap-tively Learned Graph (MALG), learning...