检索结果-内蒙古大学图书馆

OGT: optimize graph then training GNNs for node classification

NEURAL COMPUTING & APPLICATIONS 2022年第24期34卷 22209-22222页

作者： Wei, Quanmin Wang, Jinyan Hu, Jun Li, Xianxian Yi, Tong Guangxi Normal Univ Guangxi Key Lab Multisource Informat Min & Secur Guilin 541004 Guangxi Peoples R China Guangxi Normal Univ Sch Comp Sci & Engn Guilin 541004 Guangxi Peoples R China

graph Neural Networks (GNNs) have shown excellent performance in graph-related tasks and have arisen widespread attention. However, most existing works on GNNs mainly focus on proposing a novel GNN model or modifying the models to improve performance in various graph-related tasks and seldom consider possible problems in the graph data as model input data. This paper studies that low-degree nodes, accounting for most of the real-world graphs, naturally have message passing insufficiency problem due to too little information from other nodes when generating node embedding, which will affect the performance of the GNNs. To solve this problem, we propose a simple but practical method-Optimize graph Then Training (OGT), which adds edges between low-degree nodes and some nodes with the same predicted label based on the GNNs prediction results and the inherent information in the graph. The OGT aims to improve the performance of GNNs in semi-supervised node classification tasks by augmenting the input data. More importantly, the OGT is regarded as a data preprocessing technique and can be used naturally with baseline GNN models (e.g., GCN, GAT, graphSAGE, and SGC) to improve the performance of these models without making other modifications. Extensive experiments on three benchmark citation datasets with five typical GNN models verify that OGT consistently improves the performance of various GNNs to a great extent, where 1.9% (Cora), 1.0% (Citeseer), and 1.3% (Pubmed) average accuracy improvement on the node classification task.

关键词： graph neural networks Semi-supervised node classification graph-structured data Node embedding generation

来源：评论

学校读者我要写书评

暂无评论

An Effective Keyword Search Method for graph-structured data Using Extended Answer Structure

An Effective Keyword Search Method for Graph-Structured Data...

引用

13th International Conference on Computational Science and Its Applications (ICCSA)

作者： Park, Chang-Sup Dongduk Womens Univ Seoul South Korea

ISBN: (纸本)9783642396403

This paper proposes an effective approach to ranked keyword search over graph-structured data which is getting much attraction in various applications. To provide more effective search results than the previous approaches, we suggest an extended answer structure which has no constraint on the number of keyword nodes and is based on a new relevance measure. For efficient keyword search, we also use an inverted list index which pre-computes connectivity and relevance information on the nodes in the graph. We present a query processing algorithm based on the pre-constructed inverted lists, which aggregates entries relevant to each node and finds top-k answer trees relevant to the given query. We also enhance the basic search method by storing additional information on the relevance of the related entries in the lists, in order to estimate the relevance score of each node more closely and to find top-k answers more efficiently. We show by experiments that the proposed keyword search method can provide effective top-k search results over large amount of graph-structured data with good execution performance.

关键词： graph-structured data Keyword Search Top-k Query Processing

来源：评论

学校读者我要写书评

暂无评论

Streamlined Training of GCN for Node Classification with Automatic Loss Function and Optimizer Selection 1

引用

24th International Conference on Engineering Applications of Neural Networks (EANN)

作者： Sanaullah Koravuna, Shamini Rueckert, Ulrich Jungeblut, Thorsten Bielefeld Univ Appl Sci Bielefeld Germany Bielefeld Univ Bielefeld Germany

ISBN: (数字)9783031342042

ISBN: (纸本)9783031342035;9783031342042

graph Neural Networks (GNNs) are specialized neural networks that operate on graph-structured data, utilizing the connections between nodes to learn and process information. To achieve optimal performance, GNNs require the automatic selection of the best loss and optimization functions, which allows the model to adapt to the unique features of the dataset being used. This eliminates the need for manual selection, saving time and minimizing the requirement for domain-specific knowledge. The automatic selection of loss and optimization functions is a crucial factor in achieving state-of-the-art results when training GNNs. In this study, we trained graph Convolutional Networks (GCNs) and graph Attention Networks (GAT) models for node classification on three benchmark datasets. To automatically select the best loss and optimization functions, we utilized performance metrics. We implemented a learning rate scheduler to adjust the learning rate based on the model's performance, which led to improved results. We evaluated the model's performance using multiple metrics and reported the best loss function and performance metric, enabling users to compare its performance to other models. Our approach achieved state-of-the-art results, highlighting the importance of selecting the appropriate loss and optimizer functions. Additionally, we developed a real-time visualization of the GCN model during training, providing users with a detailed understanding of the model's behavior. Overall, this study provides a comprehensive understanding of GNNs and their application to graph-structured data, with a specific focus on real-time visualization of GNN behavior during training.

关键词： graph convolutional networks graph-structured data Los Functions Node classification Benchmark datasets Automatic Selection

来源：评论

学校读者我要写书评

暂无评论

Generalizing graph Neural Network across graphs and Time 23

Generalizing Graph Neural Network across Graphs and Time

引用

16th International Conference on Web Search and data Mining

作者： Wen, Zhihao Singapore Management Univ Sch Comp & Informat Syst Singapore Singapore

ISBN: (纸本)9781450394079

graph-structured data widely exist in diverse real-world scenarios, analysis of these graphs can uncover valuable insights about their respective application domains. However, most previous works focused on learning node representation from a single fixed graph, while many real-world scenarios require representations to be quickly generated for unseen nodes, new edges, or entirely new graphs. This inductive ability is essential for high-throughtput machine learning systems. However, this inductive graph representation problem is quite difficult, compared to the transductive setting, for that generalizing to unseen nodes requires new subgraphs containing the new nodes to be aligned to the neural network trained already. Meanwhile, following a message passing framework, graph neural network (GNN) is an inductive and powerful graph representation tool. We further explore inductive GNN from more specific perspectives: (1) generalizing GNN across graphs, in which we tackle with the problem of semi-supervised node classification across graphs;(2) generalizing GNN across time, in which we mainly solve the problem of temporal link prediction;(3) generalizing GNN across tasks;(4) generalizing GNN across locations.

关键词： graph-structured data graph neural network inductive

来源：评论

学校读者我要写书评

暂无评论

Construct New graphs using Information Bottleneck Against Property Inference Attacks

Construct New Graphs using Information Bottleneck Against Pr...

引用

IEEE International Conference on Communications (IEEE ICC)

作者： Zhang, Chenhan Tian, Zhiyi Yu, James J. Q. Yu, Shui Univ Technol Sydney Sch Comp Sci Sydney NSW Australia Southern Univ Sci & Technol Dept Comp Sci & Engn Shenzhen Peoples R China

ISBN: (纸本)9781538674628

graphs provide a unique representation of real-world data. However, recent studies found that inference attacks can extract private property information of graph data from trained graph neural networks (GNNs), which arouses privacy concerns about graph data, especially in collaborative learning systems where model information is more accessible. While there has been a few research efforts on the property inference attacks against GNNs, how to defend against such attacks has seldom been studied. In this paper, we propose to leverage the information bottleneck (IB) principle to defend against the property inference attacks. Particularly, we involve a threat model, where the attacker can extract graph property from the graph embedding developed by GNNs. To defend against the attacks, we use IB to construct new graph structures from the original graphs. The change in graph structures enables the new graphs to contain less information related to the property information of the original graphs, making it harder for attackers to infer property information of the original graphs from the graph embeddings. Meantime, the IB principle enables task-relevant information to be sufficiently contained in the new graph, enabling GNNs to develop accurate predictions. The experimental results demonstrate the efficacy of the proposed approach in resisting property inference attacks and developing accurate predictions.

关键词： graph-structured data graph neural networks inference attacks information bottleneck

来源：评论

学校读者我要写书评

暂无评论

Privacy-Assured Similarity Query over graph-structured data in Mobile Cloud

Privacy-Assured Similarity Query over Graph-Structured Data ...

引用

33rd IEEE International Conference on Distributed Computing Systems (ICDCS)

作者： Zhang, Yingguang Su, Sen Chen, Weifeng Wang, Yulong Xu, Peng Yang, Fangchun Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9781479932474;9780769550237

In the emerging mobile cloud paradigm, more and more innovative social applications are provided. The data of these applications is usually represented by the graph structure. For effective data retrieval, it is a crucial requirement to enable substructure similarity query over these graph-structured data. The sensitive information of the graphs and users may be leaked during the retrieval, leading to privacy violations. However, most existing works on protecting privacy pay little attention to this problem. Additionally, considering the complicated similarity computation and the privacy requirements, it is particularly challenging to solve the problem effectively. In this paper, for the first time, we investigate the problem of privacy-assured substructure similarity query over graph-structured data in mobile cloud. Our solution proposes a series of secure algorithms to effectively perform the similarity query without privacy breaches. The proposed solution first builds a secure feature-graph index to represent the feature-related information about each data graph based on privacy homomorphism and obscuration methods, and then calculates the similarity between the query graph and each data graph by the difference of feature frequency in a privacy-preserving manner. Thorough analysis is given to investigate privacy and efficiency guarantees, and the experiments further demonstrate the validity and efficiency of the proposed solution.

关键词： Substructure Similarity Query graph-structured data Mobile Cloud Privacy-assured

来源：评论

学校读者我要写书评

暂无评论

data-Efficient graph Learning

Data-Efficient Graph Learning

引用

作者： Ding, Kaize Arizona State University

学位级别：Ph.D., Doctor of Philosophy

graph-structured data, ranging from social networks to financial transaction networks, from citation networks to gene regulatory networks, have been widely used for modeling a myriad of real-world systems. As a prevailing model architecture to model graph-structured data, graph neural networks (GNNs) has drawn much attention in both academic and industrial communities in the past decades. Despite their success in different graph learning tasks, existing methods usually rely on learning from ``big'' data, requiring a large amount of labeled data for model training. However, it is common that real-world graphs are associated with ``small'' labeled data as data annotation and labeling on graphs is always time and resource-consuming. Therefore, it is imperative to investigate graph machine learning (graph ML) with low-cost human supervision for low-resource settings where limited or even no labeled data is available. This dissertation investigates a new research field -- data-Efficient graph Learning, which aims to push forward the performance boundary of graph machine learning (graph ML) models with different kinds of low-cost supervision signals. To achieve this goal, a series of studies are conducted for solving different data-efficient graph learning problems, including graph few-shot learning, graph weakly-supervised learning, and graph self-supervised learning.

关键词： data-efficient learning Few-shot learning graph neural networks Self-supervised learning Weakly-supervised learning graph-structured data

来源：评论

学校读者我要写书评

暂无评论

Fast vertex-based graph convolutional neural network and its application to brain images

引用

NEUROCOMPUTING 2021年 434卷 1-10页

作者： Liu, Chaoqiang Ji, Hui Qiu, Anqi Natl Univ Singapore Dept Biomed Engn Singapore Singapore Natl Univ Singapore Smart Syst Inst Singapore Singapore Natl Univ Singapore 1 Inst Hlth Singapore Singapore Natl Univ Singapore Dept Math Singapore Singapore Johns Hopkins Univ Dept Biomed Engn Baltimore MD 21218 USA

This paper proposes a vertex-based graph convolutional neural network (vertex-CNN) for analyzing structured data on graphs. We represent graphs using semi-regular triangulated meshes in which each vertex has 6 connected neighbors. We generalize classical CNN defined on equi-spaced grids to that defined on semi-regular triangulated meshes by introducing main building blocks of the CNN, including convolution, down-sampling, and pooling, on a vertex domain. By exploiting the regularity of semi regular meshes in terms of vertex connections, the proposed vertex-CNN keeps the inherent properties of classical CNN in a Euclidean space, such as shift-invariance and down-sampling at a rate of 2, 4, etc. We employ brain images from Alzheimer's Disease Neuroimaging Initiative (ADNI) (n = 6767) and extract cortical features (e.g., cortical thickness, surface area, curvature, Jacobian, sulcal depth, and volume) for the classification of healthy controls (CON), patients with mild cognitive impairment (MCI) and Alzheimer's disease (AD). Based on cortical thickness, we show that the proposed vertex-CNN is near 3 times faster and performs significantly better in the classification performance of CON, MCI, and AD than an existing graph CNN defined on the graph spectral domain given in Defferrard (2016). Moreover, we examine the robustness of a multi-channel implementation of vertex-CNN on 6 cortical measures for the MCI and AD classification. Finally, we show a promising finding of the prediction accuracy from MCI to AD as a function of years before the onset of AD. Our experiments demonstrate the fast computation and promising classification performance of the vertex-CNN. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Convolutional neural network graph-structured data Dementia classification Semi-triangulated meshes

来源：评论

学校读者我要写书评

暂无评论

Recgraph: graph Recovery Attack using Variational graph Autoencoders

RecGraph: Graph Recovery Attack using Variational Graph Auto...

引用

40th IEEE International Performance, Computing, and Communications Conference (IPCCC)

作者： Tian, Jing Liu, Chang Gou, Gaopeng Li, Zhen Xiong, Gang Guan, Yangyang Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9781665443319

graph-structured data contains a lot of sensitive information about individuals. In order to protect users' privacy, many anonymization mechanisms for graph-structured data are proposed. However, one common drawback of these mechanisms is that they only consider to hide the local characteristics, such as the degree of nodes or their neighbors. They lack the consideration for the nodes' attribute features and the features of potential global graph structure, which leads to the failure of these mechanisms to provide sufficient security. To address this shortcoming, we propose Recgraph, a framework for graph recovery attack based on variational graph autoencoders. We use Recgraph to perform graph recovery attack on three real social network datasets, and compare it with five existing baselines, to prove the effectiveness of our method. We also evaluate the privacy wastage after performing the graph recovery attack using Recgraph to demonstrate the serious security risks faced by the existing graph anonymization mechanisms.

关键词： graph-structured data graph recovery attack variational graph autoencoders

来源：评论

学校读者我要写书评

暂无评论

Understanding and Resolving Performance Degradation in Deep graph Convolutional Networks 21

Understanding and Resolving Performance Degradation in Deep ...

引用

30th ACM International Conference on Information and Knowledge Management (CIKM)

作者： Zhou, Kuangqi Dong, Yanfei Wang, Kaixin Lee, Wee Sun Hooi, Bryan Xu, Huan Feng, Jiashi Natl Univ Singapore Singapore Singapore PayPal Innovat Lab Singapore Singapore Alibaba Grp Hangzhou Peoples R China

ISBN: (纸本)9781450384469

A graph Convolutional Network (GCN) stacks several layers and in each layer performs a PROPagation operation (PROP) and a TRANsformation operation (TRAN) for learning node representations over graph-structured data. Though powerful, GCNs tend to suffer performance drop when the model gets deep. Previous works focus on PROPs to study and mitigate this issue, but the role of TRANs is barely investigated. In this work, we study performance degradation of GCNs by experimentally examining how stacking only TRANs or PROPs works. We find that TRANs contribute significantly, or even more than PROPs, to declining performance, and moreover that they tend to amplify node-wise feature variance in GCNs, causing variance inflammation that we identify as a key factor for causing performance drop. Motivated by such observations, we propose a variance-controlling technique termed Node Normalization (NodeNorm), which scales each node's features using its own standard deviation. Experimental results validate the effectiveness of NodeNorm on addressing performance degradation of GCNs. Specifically, it enables deep GCNs to outperform shallow ones in cases where deep models are needed, and to achieve comparable results with shallow ones on 6 benchmark datasets. NodeNorm is a generic plug-in and can well generalize to other GNN architectures. Code is publicly available at https://***/miafei/NodeNorm.

关键词： graph-structured data deep graph convolutional networks performance degradation normalization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：