Motif-aware Riemannian Graph Neural Network with Generative-Contrastive Learning(具有生成-对比学习的Motif感知黎曼图神经网络) 原文地址: https://arxiv.org/abs/2401.01232arxiv.org/abs/2401.01232 代码地址: https://github.com/RiemannGraph/MotifRGCgithub.com/RiemannGraph/MotifRGC 摘要: 图是典型...
https://github.com/RiemannGraph/MotifRGC.github.com/RiemannGraph/MotifRGC Riemannian Geometry Manifold 黎曼流形 M 是与黎曼度量耦合的光滑流形。对于每个点 x ,黎曼度量 gx 是在其切线空间 TxM 上定义的。对数映射 Logx:M→TxM 将流形中的向量转换为切线空间,而指数图 Expx 做逆变换。欧几里得空间是...
On this basis, this paper proposes a link prediction model based on motif graph neural network. The model adopts auto-encoder architecture. In the encoding process, the adjacent matrix of the node is constructed by the motif, and then the motif neighborhood of...
HGNN:Hyperbolic Graph Neural Networks, NIPS19 LGCN:Lorentzian Graph Convolutional Networks, WWW21 k-GCN:Constant Curvature Graph Convolutional Networks, ICML20. H-to-H:A Hyperbolic-to-Hyperbolic Graph Convolutional Network, CVPR21. SelfMG:我们AAAI22的工作 Q-GCN:Pseudo-Riemannian Graph Convolutional Ne...
MotifNet: a motif-based Graph Convolutional Network for directed graphs Deep learning on graphs and in particular, graph convolutional neural networks, have recently attracted significant attention in the machine learning commu... F Monti,K Otness,MM Bronstein - IEEE 被引量: 7发表: 2018年 ...
以往的方法表明通过信息在社交关系上的传播可以提高用户特别是长尾薄数据用户违约预测的准确性,然而这些方法都没有捕捉到以小型子图模式为主的高阶结构信息。我们在KDD2023中发表的论文“Financial Default Prediction via Motif-preserving Graph Neural Network with Curriculum Learning”提出一种保留motif结构的图神经网络...
近几年,图神经网络(Graph Neural Network)由于能够较好地提取网络结构信息以获得网络表示,逐渐成为网络节点分类的主流算法.然而,与广泛研究的同质信息网络相比,真实世... 吴越,王英,王鑫,... - 《计算机学报》 被引量: 0发表: 2021年 基于超图卷积的异质网络半监督节点分类 近几年,图神经网络(Graph Neural Netw...
Deep learning on graphs and in particular, graph convolutional neural networks, have recently attracted significant attention in the machine learning community. Many of such techniques explore the analogy between the graph Laplacian eigenvectors and the classical Fourier basis, allowing to formulate the co...
Particularly, Graph Neural Networks (GNNs) have demonstrated remarkable success in various molecular generation and prediction tasks. In cases where labeled data is scarce, GNNs can be pre-trained on unlabeled molecular data to first learn the general semantic and structural information before being ...
MOTIFNET: A MOTIF-BASED GRAPH CONVOLUTIONAL NETWORKFOR DIRECTED GRAPHSFederico Monti 1 , Karl Otness 2 , Michael M. Bronstein 1,2,31 University of Lugano 2 Harvard University 3 Tel Aviv UniversityABSTRACTDeep learning on graphs and in particular, graph convolu-tional neural networks, have recen...