检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Big Data, BigData 2023

作者： Koohi Esfahani, Mohsen Boldi, Paolo Vandierendonck, Hans Kilpatrick, Peter Vigna, Sebastiano Queen's University Belfast United Kingdom University of Sistan Iran Università Degli Studi di Milano Italy

ISBN: (纸本)9798350324457

Progress in High-Performance Computing in general, and High-Performance graph Processing in particular, is highly dependent on the availability of publicly-accessible, relevant, and realistic data sets. To ensure continuation of this progress, we (i) investigate and optimize the process of generating large sequence similarity graphs as an HPC challenge and (ii) demonstrate this process in creating MS-Biographs, a new family of publicly available real-world edge-weighted graph datasets with up to 2.5 trillion edges, that is, 6.6 times greater than the largest graph published recently. The largest graph is created by matching (i.e., all-toall similarity aligning) 1.7 billion protein sequences. The MSBiographs family includes also seven subgraphs with different sizes and direction types. We describe two main challenges we faced in generating large graph datasets and our solutions, that are, (i) optimizing data structures and algorithms for this multi-step process and (ii) Webgraph parallel compression technique. The datasets are available online on https://***/ DIPSA/MS-Biographs. © 2023 IEEE.

关键词： Big Data Management and Processing Biological Networks graph Algorithms graph datasets High-Performance Computing Sequence Similarity graph

来源：评论

学校读者我要写书评

暂无评论

State of the Art and Potentialities of graph-level Learning

引用

ACM COMPUTING SURVEYS 2025年第2期57卷 1-40页

作者： Yang, Zhenyu Zhang, Ge Wu, Jia Yang, Jian Sheng, Quan z. Xue, Shan Zhou, Chuan Aggarwal, Charu Peng, Hao Hu, Wenbin Hancock, Edwin Lio, Pietro Macquarie Univ Sch Comp Sydney NSW Australia Donghua Univ Sch Comp Shanghai Peoples R China Macquarie Univ Sch Comp Sydney NSW Australia Chinese Acad Sci Beijing Peoples R China IBM TJ Watson Res Ctr Off 4S A20 Hawthorne NY USA Beihang Univ Beijing Peoples R China Wuhan Univ Wuhan Peoples R China Univ York York England Univ Cambridge Cambridge England

graphs have a superior ability to represent relational data, such as chemical compounds, proteins, and social networks. Hence, graph-level learning, which takes a set of graphs as input, has been applied to many tasks, including comparison, regression, classification, and more. Traditional approaches to learning a set of graphs heavily rely on hand-crafted features, such as substructures. While these methods benefit from good interpretability, they often suffer from computational bottlenecks, as they cannot skirt the graph isomorphism problem. Conversely, deep learning has helped graph-level learning adapt to the growing scale of graphs by extracting features automatically and encoding graphs into low-dimensional representations. As a result, these deep graph learning methods have been responsible for many successes. Yet, no comprehensive survey reviews graph-level learning starting with traditional learning and moving through to the deep learning approaches. This article fills this gap and frames the representative algorithms into a systematic taxonomy covering traditional learning, graph-level deep neural networks, graph-level graph neural networks,

关键词： graph-level learning graph datasets deep Learning graph neural networks graph pooling

来源：评论

学校读者我要写书评

暂无评论

Finding Efficient graph Embeddings and Processing them by a CNN-based Tool

引用

NEURAL PROCESSING LETTERS 2024年第5期56卷 226页

作者： Tiba, Attila Hajdu, Andras Giraszi, Tamas Univ Debrecen Fac Informat Kassa Str 26 H-4028 Hajdu Bihar Hungary

We introduce new tools to support finding efficient graph embedding techniques for graph databases and to process their outputs using deep learning for classification scenarios. Accordingly, we investigate the possibility of creating an ensemble of different graph embedding methods to raise accuracy and present an interconnected neural network-based ensemble to increase the efficiency of the member classification algorithms. We also introduce a new convolutional neural network-based architecture that can be generally proposed to process vectorized graph data provided by various graph embedding methods and compare it with other architectures in the literature to show the competitiveness of our approach. We also exhibit a statistical-based inhomogeneity level estimation procedure to select the optimal embedding for a given graph database efficiently. The efficiency of our framework is exhaustively tested using several publicly available graph datasets and numerous state-of-the-art graph embedding techniques. Our experimental results for classification tasks have proved the competitiveness of our approach by outperforming the state-of-the-art frameworks.

关键词： graph embedding Ensemble of embeddings graph datasets Convolutional neural networks graph classification

来源：评论

学校读者我要写书评

暂无评论

Value is in the Eye of the Beholder: A Framework for an Equitable graph Data Evaluation 24

Value is in the Eye of the Beholder: A Framework for an Equi...

引用

6th ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT)

作者： Nerini, Francesco Paolo Bajardi, Paolo Panisson, Andre Sapienza Univ Rome DIAG Rome Italy CENTAI Inst Turin Italy

ISBN: (纸本)9798400704505

Proprietary data is a valuable asset used to develop predictive algorithms that benefit a wide range of users, including customers, business owners, and decision-makers. Consequently, there is a growing interest in developing safe and robust techniques for sharing, learning models, and distributing predictions across a wide spectrum of potential stakeholders. However, a structured process to assess the value of data assets, and thus enabling collaborations among stakeholders, remains largely unexplored. This is particularly challenging when the data to be shared has a networked structure, where increasing the shared data samples potentially connects information observed by different data owners, providing new knowledge that is unavailable to any data owner individually. Here, we propose E-GraDE, a framework that assists organizations in assessing the value of their networked data to better address graph machine learning tasks. This framework includes a step-by-step analysis of the requirements of different stakeholders, such as the accuracy or fairness requisites of the models, ensuring a fair evaluation process and stronger alignment in the development of a data federation consortium. Additionally, we propose an approach to estimate the value of networked data to be shared while disclosing only a small fraction of the original information. We support our approach with extensive computational experiments, analysing each part of it through simulated use cases.

关键词： Dataset Evaluation graph datasets graph Neural Networks Shapley Values

来源：评论

学校读者我要写书评

暂无评论

graph partitioning and visualization in graph mining: a survey

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第30期81卷 43315-43356页

作者： Bhavsar, Swati A. Patil, Varsha H. Patil, Aboli H. SavitribaiPhule Pune Univ MCERC Res Ctr Dept Comp Engn Nasik India

graph mining is a process of obtaining one or more sub-graphs and has been a very attractive research topic over the last two decades. It has found many practical applications dealing with real world problems in variety of domains like Social Network Analysis, Designing of Computer Networks, Study of Chemical Reactions, Bio Informatics, Program Flow Structures, Image Processing, Enterprise data, Sparse Matrix ordering and many more. For these applications, many graph classification and graph Clustering algorithms are evolved. This paper presents a comprehensive survey of published work in graph Mining by grouping them in a broad taxonomy. For each of these groups in the taxonomy, the basic concepts of the algorithms are covered in detail by mentioning the contributions of various authors to the basic concepts of each group. Furthermore, common issues in graph mining algorithms, such as clustering, partitioning, visualization of graphs, are also elaborated. Standard datasets available for graph mining are stated as well.

关键词： graph mining graph classification graph partitioning graph datasets

来源：评论

学校读者我要写书评

暂无评论

Dataset Announcement: MS-Biographs, Trillion-Scale Public Real-World Sequence Similarity graphs 26

Dataset Announcement: MS-BioGraphs, Trillion-Scale Public Re...

引用

26th IEEE International Symposium on Workload Characterization (IISWC)

作者： Esfahani, Mohsen Koohi Boldi, Paolo Vandierendonck, Hans Kilpatrick, Peter Vigna, Sebastiano Queens Univ Belfast Belfast Antrim North Ireland Univ Milan Milan Italy Univ Sistan Zahedan Iran

ISBN: (纸本)9798350303179

Progress in High-Performance Computing in general, and High-Performance graph Processing in particular, is highly dependent on the availability of publicly-accessible, relevant, and realistic data sets. In this paper, we announce publication of MS-Biographs, a new family of publicly-available real-world edge-weighted graph datasets with up to 2.5 trillion edges, that is, 6.6 times greater than the largest graph published recently. We briefly review the two main challenges we faced in generating large graph datasets and our solutions, that are, (i) optimizing data structures and algorithms for this multi-step process and (ii) Webgraph parallel compression technique. We also study some characteristics of MS-Biographs. The datasets and the complete version of this paper are available on https://***/DIPSA/MS-Biographs.

关键词： graph datasets High-Performance graph Processing High-Performance Computing Biological Networks Sequence Similarity graph

来源：评论

学校读者我要写书评

暂无评论

Guarantees of Differential Privacy in Cloud of Things: A Multilevel Data Publication Scheme

引用

INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH IN AFRICA 2021年第1期56卷 199-212页

作者： Ngangmo, Olga Kengni Ari, Ado Adamou Abba Mohamadou, BAlidou Thiare, Ousmane Kolyang Univ Maroua LaRI Lab POB 814 Maroua Cameroon Univ Versailles St Quentin En Yvelines Univ Paris Saclay LI PaRAD Lab 45 Ave Etats Unis F-78035 Versailles France Gaston Berger Univ St Louis LANI Lab POB 234 St Louis Senegal

Nowadays, the cloud computing technology combined with the new generation networks and internet of things facilitate the networking of numerous smart devices. Moreover, the advent of the smart web requires massive data backup from the smart connected devices to the cloud. Unfortunately, the publication of several of these data, such as medical information and financial transactions, could lead to serious privacy breaches, which is becoming the most serious issue in cloud of things. For instance, passive attacks can launched in order to get access to private information. For this reason, several data anonymization techniques have emerged in order to keep data as confidential as possible. However, these different techniques are making the data unusable the most of time. Meanwhile, differential privacy that has been used in a number of cyber physical systems recently emerged as an efficient technique for ensuring the privacy of cloud of things stored data. In this exploratory paper, we study the guarantees of differential privacy of a multi-level anonymization scheme of data graphs. The considered scheme disturbs the structure of the graph by adding false edges, groups the vertices in distinct sets and permutes the vertices in these groups. Particularly, we demonstrated the guarantees that the anonymized data by this algorithm remain exploitable while guaranteeing the anonymity of users.

关键词： Differential Privacy Anonymization Cloud of Things graph datasets

来源：评论

学校读者我要写书评

暂无评论

graph classification via discriminative edge feature learning

引用

PATTERN RECOGNITION 2023年第1期143卷

作者： Yi, Yang Lu, Xuequan Gao, Shang Robles-Kelly, Antonio Zhang, Yuejie Deakin Univ Sch Informat Technol Waurn Ponds Vic 3216 Australia Fudan Univ Sch Comp Sci Shanghai 200433 Peoples R China

Spectral graph convolutional neural networks (GCNNs) have been producing encouraging results in graph classification tasks. However, most spectral GCNNs utilize fixed graphs when aggregating node features while omitting edge feature learning and failing to get an optimal graph structure. Moreover, many ex-isting graph datasets do not provide initialized edge features, further restraining the ability of learning edge features via spectral GCNNs. In this paper, we try to address this issue by designing an edge fea-ture scheme and an add-on layer between every two stacked graph convolution layers in spectral GCNN. Both are lightweight while effective in filling the gap between edge feature learning and performance enhancement of graph classification. The edge feature scheme makes edge features adapt to node repre-sentations at different spectral graph convolution layers. The add-on layer helps adjust the edge features to an optimal graph structure. To test the effectiveness of our method, we take Euclidean positions as initial node features and extract graphs with semantic information from point cloud objects. The node features of our extracted graphs are more scalable for edge feature learning than most existing graph datasets (in one-hot encoded label format). Three new graph datasets are constructed based on Model-Net40, ModelNet10 and ShapeNet Part datasets. Experimental results show that our method outperforms state-of-the-art graph classification methods on the new datasets. Our code and the constructed graph datasets will be released to the community.& COPY;2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license ( http://***/licenses/by-nc-nd/4.0/ )

关键词： GCNNs graph construction graph datasets graph classification

来源：评论

学校读者我要写书评

暂无评论

Benchmarking graph neural networks

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 1730-1777页

作者： Vijay Prakash Dwivedi Chaitanya K. Joshi Anh Tuan Luu Thomas Laurent Yoshua Bengio Xavier Bresson Nanyang Technological University Singapore University of Cambridge UK Loyola Marymount University Mila University of Montréal Canada National University of Singapore

In the last few years, graph neural networks (GNNs) have become the standard toolkit for analyzing and learning from data on graphs. This emerging field has witnessed an extensive growth of promising techniques that have been applied with success to computer science, mathematics, biology, physics and chemistry. But for any successful field to become mainstream and reliable, benchmarks must be developed to quantify progress. This led us in March 2020 to release a benchmark framework that i) comprises of a diverse collection of mathematical and real-world graphs, ii) enables fair model comparison with the same parameter budget to identify key architectures, iii) has an open-source, easy-to-use and reproducible code infrastructure, and iv) is flexible for researchers to experiment with new theoretical ideas. As of December 2022, the GitHub repository1 has reached 2,000 stars and 380 forks, which demonstrates the utility of the proposed open-source framework through the wide usage by the GNN community. In this paper, we present an updated version of our benchmark with a concise presentation of the aforementioned framework characteristics, an additional medium-sized molecular dataset AQSOL, similar to the popular ZINC, but with a real-world measured chemical target, and discuss how this framework can be leveraged to explore new GNN designs and insights. As a proof of value of our benchmark, we study the case of graph positional encoding (PE) in GNNs, which was introduced with this benchmark and has since spurred interest of exploring more powerful PE for Transformers and GNNs in a robust experimental setting.

关键词： graph neural networks benchmarking graph datasets exploration tool

来源：评论

学校读者我要写书评

暂无评论

graph Processing on GPUs: A Survey

引用

ACM COMPUTING SURVEYS 2018年第6期50卷 1-35页

作者： Shi, Xuanhua Zheng, Zhigao Zhou, Yongluan Jin, Hai He, Ligang Liu, Bo Hua, Qiang-Sheng Huazhong Univ Sci & Technol Sch Comp Sci & Technol Serv Comp Technol & Syst Lab Big Data Technol & Syst Lab 1037Luoyu Rd Wuhan Hubei Peoples R China Univ Copenhagen Dept Comp Sci Univ Pk 5 DK-2100 Copenhagen Denmark Univ Warwick Dept Comp Sci Coventry CV4 7AL W Midlands England

In the big data era, much real-world data can be naturally represented as graphs. Consequently, many application domains can be modeled as graph processing. graph processing, especially the processing of the large-scale graphs with the number of vertices and edges in the order of billions or even hundreds of billions, has attracted much attention in both industry and academia. It still remains a great challenge to process such large-scale graphs. Researchers have been seeking for new possible solutions. Because of the massive degree of parallelism and the high memory access bandwidth in GPU, utilizing GPU to accelerate graph processing proves to be a promising solution. This article surveys the key issues of graph processing on GPUs, including data layout, memory access pattern, workload mapping, and specific GPU programming. In this article, we summarize the state-of-the-art research on GPU-based graph processing, analyze the existing challenges in detail, and explore the research opportunities for the future.

关键词： graph processing GPU graph datasets parallelism BSP model GAS model

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：