The existing graph convolution methods usually suffer high computational burdens,large memory requirements,and intractable batch-processing.In this paper,we propose a high-efficient variational gridded graph convoluti...The existing graph convolution methods usually suffer high computational burdens,large memory requirements,and intractable batch-processing.In this paper,we propose a high-efficient variational gridded graph convolution network(VG-GCN)to encode non-regular graph data,which overcomes all these aforementioned problems.To capture graph topology structures efficiently,in the proposed framework,we propose a hierarchically-coarsened random walk(hcr-walk)by taking advantage of the classic random walk and node/edge encapsulation.The hcr-walk greatly mitigates the problem of exponentially explosive sampling times which occur in the classic version,while preserving graph structures well.To efficiently encode local hcr-walk around one reference node,we project hcrwalk into an ordered space to form image-like grid data,which favors those conventional convolution networks.Instead of the direct 2-D convolution filtering,a variational convolution block(VCB)is designed to model the distribution of the randomsampling hcr-walk inspired by the well-formulated variational inference.We experimentally validate the efficiency and effectiveness of our proposed VG-GCN,which has high computation speed,and the comparable or even better performance when compared with baseline GCNs.展开更多
Graph conjoint attention(CAT)network is one of the best graph convolutional networks(GCNs)frameworks,which uses a weighting mechanism to identify important neighbor nodes.However,this weighting mechanism is learned ba...Graph conjoint attention(CAT)network is one of the best graph convolutional networks(GCNs)frameworks,which uses a weighting mechanism to identify important neighbor nodes.However,this weighting mechanism is learned based on static information,which means it is susceptible to noisy nodes and edges,resulting in significant limitations.In this paper,a method is proposed to obtain context dynamically based on random walk,which allows the context-based weighting mechanism to better avoid noise interference.Furthermore,the proposed context-based weighting mechanism is combined with the node content-based weighting mechanism of the graph attention(GAT)network to form a model based on a mixed weighting mechanism.The model is named as the context-based and content-based graph convolutional network(CCGCN).CCGCN can better discover important neighbors,eliminate noise edges,and learn node embedding by message passing.Experiments show that CCGCN achieves state-of-the-art performance on node classification tasks in multiple datasets.展开更多
为解决目前基于节点采样的图池化方法中所存在的评估节点重要性的策略过于简单以及子结构特征信息大量丢失等问题,提出了基于节点采样的子结构代表层次池化模型(sub-structure representative hierarchical pooling model based on node...为解决目前基于节点采样的图池化方法中所存在的评估节点重要性的策略过于简单以及子结构特征信息大量丢失等问题,提出了基于节点采样的子结构代表层次池化模型(sub-structure representative hierarchical pooling model based on node sampling,SsrPool)。该模型主要包括子结构代表节点选择模块和子结构代表节点特征生成模块2个部分。首先,子结构代表节点选择模块同时考虑了节点特征信息以及结构信息,利用不同方法评估节点重要性并通过不同重要性分数协作产生鲁棒的节点排名以指导节点选择。其次,子结构代表节点特征生成模块通过特征融合保留局部子结构特征信息。通过将SsrPool与现有神经网络相结合,在不同规模公共数据集上的图分类实验结果证明了SsrPool的有效性。展开更多
Node classification has a wide range of application scenarios such as citation analysis and social network analysis.In many real-world attributed networks,a large portion of classes only contain limited labeled nodes....Node classification has a wide range of application scenarios such as citation analysis and social network analysis.In many real-world attributed networks,a large portion of classes only contain limited labeled nodes.Most of the existing node classification methods cannot be used for few-shot node classification.To train the model effectively and improve the robustness and reliability of the model with scarce labeled samples,in this paper,we propose a local adaptive discriminant structure learning(LADSL)method for few-shot node classification.LADSL aims to properly represent the nodes in the attributed graphs and learn a metric space with a strong discriminating power by reducing the intra-class variations and enlargingginter-classdifferences.Extensiveexperiments conducted on various attributed networks datasets demonstrate that LADSL is superior to the other methods on few-shot node classification task.展开更多
基金supported by the Natural Science Foundation of Jiangsu Province(BK20190019,BK20190452)the National Natural Science Foundation of China(62072244,61906094)the Natural Science Foundation of Shandong Province(ZR2020LZH008)。
文摘The existing graph convolution methods usually suffer high computational burdens,large memory requirements,and intractable batch-processing.In this paper,we propose a high-efficient variational gridded graph convolution network(VG-GCN)to encode non-regular graph data,which overcomes all these aforementioned problems.To capture graph topology structures efficiently,in the proposed framework,we propose a hierarchically-coarsened random walk(hcr-walk)by taking advantage of the classic random walk and node/edge encapsulation.The hcr-walk greatly mitigates the problem of exponentially explosive sampling times which occur in the classic version,while preserving graph structures well.To efficiently encode local hcr-walk around one reference node,we project hcrwalk into an ordered space to form image-like grid data,which favors those conventional convolution networks.Instead of the direct 2-D convolution filtering,a variational convolution block(VCB)is designed to model the distribution of the randomsampling hcr-walk inspired by the well-formulated variational inference.We experimentally validate the efficiency and effectiveness of our proposed VG-GCN,which has high computation speed,and the comparable or even better performance when compared with baseline GCNs.
基金Supported by the Natural Science Foundation of Xiamen (3502Z20227067)。
文摘Graph conjoint attention(CAT)network is one of the best graph convolutional networks(GCNs)frameworks,which uses a weighting mechanism to identify important neighbor nodes.However,this weighting mechanism is learned based on static information,which means it is susceptible to noisy nodes and edges,resulting in significant limitations.In this paper,a method is proposed to obtain context dynamically based on random walk,which allows the context-based weighting mechanism to better avoid noise interference.Furthermore,the proposed context-based weighting mechanism is combined with the node content-based weighting mechanism of the graph attention(GAT)network to form a model based on a mixed weighting mechanism.The model is named as the context-based and content-based graph convolutional network(CCGCN).CCGCN can better discover important neighbors,eliminate noise edges,and learn node embedding by message passing.Experiments show that CCGCN achieves state-of-the-art performance on node classification tasks in multiple datasets.
文摘为解决目前基于节点采样的图池化方法中所存在的评估节点重要性的策略过于简单以及子结构特征信息大量丢失等问题,提出了基于节点采样的子结构代表层次池化模型(sub-structure representative hierarchical pooling model based on node sampling,SsrPool)。该模型主要包括子结构代表节点选择模块和子结构代表节点特征生成模块2个部分。首先,子结构代表节点选择模块同时考虑了节点特征信息以及结构信息,利用不同方法评估节点重要性并通过不同重要性分数协作产生鲁棒的节点排名以指导节点选择。其次,子结构代表节点特征生成模块通过特征融合保留局部子结构特征信息。通过将SsrPool与现有神经网络相结合,在不同规模公共数据集上的图分类实验结果证明了SsrPool的有效性。
基金supported by the National Key R&D Program of China(2018YFB1402600)the National Natural Science Foundation of China(Grant Nos.61802028,62192784,61877006,and 62002027)。
文摘Node classification has a wide range of application scenarios such as citation analysis and social network analysis.In many real-world attributed networks,a large portion of classes only contain limited labeled nodes.Most of the existing node classification methods cannot be used for few-shot node classification.To train the model effectively and improve the robustness and reliability of the model with scarce labeled samples,in this paper,we propose a local adaptive discriminant structure learning(LADSL)method for few-shot node classification.LADSL aims to properly represent the nodes in the attributed graphs and learn a metric space with a strong discriminating power by reducing the intra-class variations and enlargingginter-classdifferences.Extensiveexperiments conducted on various attributed networks datasets demonstrate that LADSL is superior to the other methods on few-shot node classification task.
