The goal of privacy-preserving social graph release is to protect individual privacy while preserving data util-ity.Community structure,which is an important global pattern of nodes,is a crucial data utility as it is ...The goal of privacy-preserving social graph release is to protect individual privacy while preserving data util-ity.Community structure,which is an important global pattern of nodes,is a crucial data utility as it is fundamental to many graph analysis tasks.Yet,most existing methods with differential privacy(DP)commonly fall into edge-DP to sacri-fice security in exchange for utility.Moreover,they reconstruct graphs from the local feature-extraction of nodes,resulting in poor community preservation.Motivated by this,we develop PrivCom,a strict node-DP graph release algorithm to maximize the utility on the community structure while maintaining a higher level of privacy.In this algorithm,to reduce the huge sensitivity,we devise a Katz index based private graph feature extraction method,which can capture global graph structure features while greatly reducing the global sensitivity via a sensitivity regulation strategy.Yet,under the condition that the sensitivity is fixed,the feature captured by the Katz index,which is presented in matrix form,requires privacy budget splits.As a result,plenty of noise is injected,mitigating global structural utility.To bridge this gap,we de-sign a private eigenvector estimation method,which yields noisy eigenvectors from extracted low-dimensional vectors.Then,a dynamic privacy budget allocation method with provable utility guarantees is developed to preserve the inherent relationship between eigenvalues and eigenvectors,so that the utility of the generated noise Katz matrix is well main-tained.Finally,we reconstruct the synthetic graph via calculating its Laplacian with the noisy Katz matrix.Experimental results confirm our theoretical findings and the efficacy of PrivCom.展开更多
The advent of the time of big data along with social networks makes the visualization and analysis of networks information become increasingly important in many fields. Based on the information from social networks, t...The advent of the time of big data along with social networks makes the visualization and analysis of networks information become increasingly important in many fields. Based on the information from social networks, the idea of information visualization and development of tools are presented. Popular social network micro-blog （＇Weibo＇） is chosen to realize the process of users＇ interest and communications data analysis. User interest visualization methods are discussed and chosen and programs are developed to collect users＇ interest and describe it by graph. The visualization results may be used to provide the commercial recommendation or social investigation application for decision makers.展开更多
At present, the emotion classification method of Weibo public opinions based on graph neural network cannot solve the polysemy problem well, and the scale of global graph with fixed weight is too large. This paper pro...At present, the emotion classification method of Weibo public opinions based on graph neural network cannot solve the polysemy problem well, and the scale of global graph with fixed weight is too large. This paper proposes a feature fusion network model Bert-TextLevelGCN based on BERT pre-training and improved TextGCN. On the one hand, Bert is introduced to obtain the initial vector input of graph neural network containing rich semantic features. On the other hand, the global graph connection window of traditional TextGCN is reduced to the text level, and the message propagation mechanism of global sharing is applied. Finally, the output vector of BERT and TextLevelGCN is fused by interpolation update method, and a more robust mapping of positive and negative sentiment classification of public opinion text of “Tangshan Barbecue Restaurant beating people” is obtained. In the context of the national anti-gang campaign, it is of great significance to accurately and efficiently analyze the emotional characteristics of public opinion in sudden social violence events with bad social impact, which is of great significance to improve the government’s public opinion warning and response ability to public opinion in sudden social security events. .展开更多
为了缓解推荐系统中不同用户社交空间与兴趣空间的内在信息差异和忽视高阶邻居的问题,提出了一种融合用户社交关系的自适应图卷积推荐算法(adaptive graph convolutional recommendation algorithm integrating user social relationshi...为了缓解推荐系统中不同用户社交空间与兴趣空间的内在信息差异和忽视高阶邻居的问题,提出了一种融合用户社交关系的自适应图卷积推荐算法(adaptive graph convolutional recommendation algorithm integrating user social relationships,AGCRSR)。首先,模型在嵌入层使用映射矩阵将初始特征向量转换为自适应嵌入;其次,引入注意力机制聚合不同方面的用户嵌入,通过图卷积网络来线性学习用户和项目的潜在表示;最后,通过自适应模块聚合用户表示并利用内积函数预测用户对项目的最终推荐结果。在数据集LastFM和Ciao上与其他基线算法进行了对比实验,实验结果表明AGCRSR的推荐效果较其他算法有显著提升。展开更多
基金A preliminary version of the paper was published in the Proceedings of ICDM 2020supported by the National Natural Science Foundation of China under Grant No.61772131the Science and Technology Project of the State Grid Corporation of China under Grant No.5700-202018268A-0-0-00.
文摘The goal of privacy-preserving social graph release is to protect individual privacy while preserving data util-ity.Community structure,which is an important global pattern of nodes,is a crucial data utility as it is fundamental to many graph analysis tasks.Yet,most existing methods with differential privacy(DP)commonly fall into edge-DP to sacri-fice security in exchange for utility.Moreover,they reconstruct graphs from the local feature-extraction of nodes,resulting in poor community preservation.Motivated by this,we develop PrivCom,a strict node-DP graph release algorithm to maximize the utility on the community structure while maintaining a higher level of privacy.In this algorithm,to reduce the huge sensitivity,we devise a Katz index based private graph feature extraction method,which can capture global graph structure features while greatly reducing the global sensitivity via a sensitivity regulation strategy.Yet,under the condition that the sensitivity is fixed,the feature captured by the Katz index,which is presented in matrix form,requires privacy budget splits.As a result,plenty of noise is injected,mitigating global structural utility.To bridge this gap,we de-sign a private eigenvector estimation method,which yields noisy eigenvectors from extracted low-dimensional vectors.Then,a dynamic privacy budget allocation method with provable utility guarantees is developed to preserve the inherent relationship between eigenvalues and eigenvectors,so that the utility of the generated noise Katz matrix is well main-tained.Finally,we reconstruct the synthetic graph via calculating its Laplacian with the noisy Katz matrix.Experimental results confirm our theoretical findings and the efficacy of PrivCom.
文摘The advent of the time of big data along with social networks makes the visualization and analysis of networks information become increasingly important in many fields. Based on the information from social networks, the idea of information visualization and development of tools are presented. Popular social network micro-blog （＇Weibo＇） is chosen to realize the process of users＇ interest and communications data analysis. User interest visualization methods are discussed and chosen and programs are developed to collect users＇ interest and describe it by graph. The visualization results may be used to provide the commercial recommendation or social investigation application for decision makers.
文摘At present, the emotion classification method of Weibo public opinions based on graph neural network cannot solve the polysemy problem well, and the scale of global graph with fixed weight is too large. This paper proposes a feature fusion network model Bert-TextLevelGCN based on BERT pre-training and improved TextGCN. On the one hand, Bert is introduced to obtain the initial vector input of graph neural network containing rich semantic features. On the other hand, the global graph connection window of traditional TextGCN is reduced to the text level, and the message propagation mechanism of global sharing is applied. Finally, the output vector of BERT and TextLevelGCN is fused by interpolation update method, and a more robust mapping of positive and negative sentiment classification of public opinion text of “Tangshan Barbecue Restaurant beating people” is obtained. In the context of the national anti-gang campaign, it is of great significance to accurately and efficiently analyze the emotional characteristics of public opinion in sudden social violence events with bad social impact, which is of great significance to improve the government’s public opinion warning and response ability to public opinion in sudden social security events. .
文摘为了缓解推荐系统中不同用户社交空间与兴趣空间的内在信息差异和忽视高阶邻居的问题,提出了一种融合用户社交关系的自适应图卷积推荐算法(adaptive graph convolutional recommendation algorithm integrating user social relationships,AGCRSR)。首先,模型在嵌入层使用映射矩阵将初始特征向量转换为自适应嵌入;其次,引入注意力机制聚合不同方面的用户嵌入,通过图卷积网络来线性学习用户和项目的潜在表示;最后,通过自适应模块聚合用户表示并利用内积函数预测用户对项目的最终推荐结果。在数据集LastFM和Ciao上与其他基线算法进行了对比实验,实验结果表明AGCRSR的推荐效果较其他算法有显著提升。
