检索结果-内蒙古大学图书馆

1st World Conference on Explainable Artificial Intelligence (XAI)

作者： Borile, Claudio Perotti, Alan Panisson, Andre CENTAI Inst Corso Inghilterra 3 I-10138 Turin Italy

ISBN: (纸本)9783031440663;9783031440670

graph machine learning (GML) has numerous applications, such as node/graph classification and link prediction, in real-world domains. Providing human-understandable explanations for GML models is a challenging yet fundamental task to foster their adoption, but validating explanations for link prediction models has received little attention. In this paper, we provide quantitative metrics to assess the quality of link prediction explanations, with or without ground-truth. State-of-the-art explainability methods for graph Neural Networks are evaluated using these metrics. We discuss how underlying assumptions and technical details specific to the link prediction task, such as the choice of distance between node embeddings, can influence the quality of the explanations.

关键词： graph machine learning Explainable Artificial Intelligence Link Prediction Explanation Evaluation

来源：评论

学校读者我要写书评

暂无评论

Node Classification Beyond Homophily: Towards a General Solution 23

Node Classification Beyond Homophily: Towards a General Solu...

引用

29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)

作者： Xu, Zhe Chen, Yuzhong Zhou, Qinghai Wu, Yuhang Pan, Menghai Yang, Hao Tong, Hanghang Univ Illinois Champaign IL 61820 USA Visa Res Palo Alto CA 94306 USA

ISBN: (纸本)9798400701030

graph neural networks (GNNs) have become core building blocks behind a myriad of graph learning tasks. The vast majority of the existing GNNs are built upon, either implicitly or explicitly, the homophily assumption, which is not always true and could heavily degrade the performance of learning tasks. In response, GNNs tailored for heterophilic graphs have been developed. However, most of the existing works are designed for the specific GNN models to address heterophily, which lacks generality. In this paper, we study the problem from the structure learning perspective and propose a family of general solutions named ALT. It can work hand in hand with most of the existing GNNs to handle graphs with either low or high homophily. At the core of our method is learning to (1) decompose a given graph into two components, (2) extract complementary graph signals from these two components, and (3) adaptively integrate the graph signals for node classification. Moreover, analysis based on graph signal processing shows that our framework can empower a broad range of existing GNNs to have adaptive filter characteristics and further modulate the input graph signals, which is critical for handling complex homophilic/heterophilic patterns. The proposed ALT brings significant and consistent performance improvement in node classification for a wide range of GNNs over a variety of real-world datasets.

关键词： graph machine learning graph data augmentation graph neural network node classification

来源：评论

学校读者我要写书评

暂无评论

Data-Efficient graph learning Meets Ethical Challenges 23

Data-Efficient Graph Learning Meets Ethical Challenges

引用

16th International Conference on Web Search and Data Mining

作者： Tang, Tao Federat Univ Australia Ballarat Vic Australia

ISBN: (纸本)9781450394079

Recommender systems have achieved great success in our daily life. In recent years, the ethical concerns of AI systems have gained lots of attention. At the same time, graph learning techniques are powerful in modelling the complex relations among users and items under recommender system applications. These graph learning-based methods are data hungry, which brought a significant data efficiency challenge. In this proposal, I introduce my PhD research from three aspects: 1) Efficient privacy-preserving recommendation for imbalanced data. 2) Efficient recommendation model training for Insufficient samples. 3) Explainability in the social recommendation. Challenges and solutions of the above research problems have been proposed in this proposal.

关键词： graph machine learning responsible recommendation ethical challenges

来源：评论

学校读者我要写书评

暂无评论

Exploring Fake News Detection with Heterogeneous Social Media Context graphs 1

引用

45th European Conference on Information Retrieval (ECIR)

作者： Donabauer, Gregor Kruschwitz, Udo Univ Regensburg Informat Sci Regensburg Germany

ISBN: (数字)9783031282386

ISBN: (纸本)9783031282379;9783031282386

Fake news detection has become a research area that goes way beyond a purely academic interest as it has direct implications on our society as a whole. Recent advances have primarily focused on text-based approaches. However, it has become clear that to be effective one needs to incorporate additional, contextual information such as spreading behaviour of news articles and user interaction patterns on social media. We propose to construct heterogeneous social context graphs around news articles and reformulate the problem as a graph classification task. Exploring the incorporation of different types of information (to get an idea as to what level of social context is most effective) and using different graph neural network architectures indicates that this approach is highly effective with robust results on a common benchmark dataset.

关键词： Fake news detection Social media networks graph machine learning

来源：评论

学校读者我要写书评

暂无评论

Precedability Prediction Between Open Educational Resources 24

Precedability Prediction Between Open Educational Resources

引用

4th International Conference on Information Technology for Social Good (GoodIT)

作者： Bazouzi, Aymen Le Capitaine, Hoel Miklos, Zoltan Foursov, Mickael Univ Rennes CNRS IRISA Rennes France Nantes Univ CNRS LS2N Nantes France

ISBN: (纸本)9798400710940

The abundance of Educational Resources (ERs) has allowed people to have access to a vast amount of knowledge. However, it can be difficult, for both educators and learners, to navigate through these resources. One way to facilitate navigation is to identify useful relations between these resources. This can improve the teaching and learning experiences by allowing the users to go from one resource to another based on the identified relations, such as precedence. In this work, we introduce the notion of precedability between educational resources;whether a resource A can precede another resource B. Then, we propose a two-step method to identify precedability relations between educational resources. Our method structures the educational resources in an enriched Knowledge graph (KG). Then, it uses a graph Neural Network (GNN) model to predict precedability relations. Our method performed better than multiple baselines on different benchmarks.

关键词： Educational Resources Knowledge graphs graph machine learning

来源：评论

学校读者我要写书评

暂无评论

A parameterised model for link prediction using node centrality and similarity measure based on graph embedding

引用

NEUROCOMPUTING 2024年 593卷

作者： Lu, Haohui Uddin, Shahadat Univ Sydney Fac Engn Sch Project Management Level 221 Ross St Forest Lodge NSW 2037 Australia

Link prediction is a crucial aspect of graph machine learning, with applications as diverse as disease prediction, social network recommendations, and drug discovery. It involves the prediction of potential new links between nodes within a network. Despite its importance, current models for link prediction exhibit notable limitations. graph Convolutional Networks have shown high efficiency in link prediction across various datasets. However, they face significant challenges when applied to short-path networks and ego networks, resulting in poor performance. This issue represents a critical area of concern that our work seeks to address. This paper introduces the Node Centrality and Similarity-based Parameterised Model (NCSM), a novel method for link prediction tasks. NCSM uniquely integrates node centrality and similarity measures as edge features in a customised graph Neural Network (GNN) layer, effectively leveraging the topological information of large networks. This model represents the first parameterised GNN-based link prediction model that considers topological information. The proposed model was evaluated on five benchmark graph datasets, each comprising thousands of nodes and edges. Experimental results highlight NCSM's superiority over existing state-of-the-art models like graph Convolutional Networks and Variational graph Autoencoder, as it outperforms them across various metrics and datasets. This exceptional performance can be attributed to NCSM's innovative integration of node centrality, similarity measures, and its efficient use of topological information.

关键词： graph machine learning Link prediction Network analysis Parameterised model

来源：评论

学校读者我要写书评

暂无评论

A framework for analyzing the effects of modifiable areal unit problem on ecological security pattern

引用

JOURNAL OF CLEANER PRODUCTION 2024年 458卷

作者： Jiao, Zhenzhi Wu, Zhuo Luo, Yifan Wei, Baojing Dai, Zhaolong Li, Shaoying Guangzhou Univ Sch Geog & Remote Sensing Guangzhou 510006 Peoples R China Cent South Univ Forestry & Technol CSUFT Inst Urban & Rural Landscape Ecol Coll Landscape Architecture Yuelushan Lab Variety Innovat CtrHunan Prov Big D Changsha 410004 Peoples R China CSUFT Coll Life Sci & Technol Natl Engn Lab Appl Technol Forestry & Ecol South C Changsha 410004 Hunan Peoples R China Guangzhou Univ Guangzhou Higher Educ Mega Ctr Sch Geog & Remote Sensing 230 Wai Huan Xi Rd Guangzhou 510006 Peoples R China

Ecological security pattern (ESP) provide a solution to balance ecosystems and urban development. The modifiable areal unit problem (MAUP) is a well-known geographical issue that affects the understanding of ecological processes and the results of spatial modeling. However, only a few studies have explicitly clarified the effects of MAUP on ESP. Herein, we propose new methods for identifying ecological sources and mapping the resistance surface, as well as a framework for analyzing the effects of MAUP on ESP. Our results indicate that (1) the datasets used for identifying ecological sources should possess a grain size of smaller than 300 x 300 m2. (2) The resistance surface directly influenced the results of the ecological corridors and nodes. (3) MAUP could generate uncertainties in ESP policymaking. Additionally, this study developed comprehensive network analysis tools based on graph machine learning to analyze the effect of MAUP on ESP policymaking, which can provide important landscape planning. The network analysis approaches may help policymakers gain a comprehensive understanding of the ESP network to improve the credibility of policies.

关键词： Modifiable areal unit problem Ecological security pattern graph machine learning Uncertainty Landscape planning

来源：评论

学校读者我要写书评

暂无评论

Topology-Aware Reliability Assessment by graph Neural Networks 3

Topology-Aware Reliability Assessment by Graph Neural Networ...

引用

IEEE Kansas Power and Energy Conference (KPEC)

作者： Zhu, Yongli Singh, Chanan Texas A&M Univ Elect & Comp Engn College Stn TX 77843 USA

ISBN: (纸本)9781665465915

This paper presents a preliminary study on bulk power system reliability assessment using graph neural networks. The proposed method is an end-to-end pipeline that can directly predict the reliability index. The Monte Carlo simulation and the end-to-end machine learning paradigm for bulk power system reliability assessment are introduced. Then, the basic principles of graph signal processing and graph neural networks are explained. Dataset generation and feature engineering for applying graph neural networks on end-to-end reliability assessment under situations of system topology-change are illustrated in detail. Experiment results on the RTS-79 system by the proposed graph neural networks pipeline demonstrate an obvious speed improvement over the regular Monte Carlo simulation method with acceptable prediction errors. Future research directions are also suggested in the final section.

关键词： graph neural networks graph machine learning reliability assessment topology-aware Monte Carlo simulation

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous data augmentation in graph contrastive learning for effective negative samples

引用

COMPUTERS & ELECTRICAL ENGINEERING 2024年第PartA期118卷

作者： Ali, Adnan Li, Jinlong Chen, Huanhuan Univ Sci & Technol China Sch Comp Sci & Technol Jinzhai Rd Hefei 230026 Anhui Peoples R China

graph contrastive learning (GCL) aims to contrast positive-negative counterparts, whereas graph data augmentation (GDA) in GCL is employed to generate positive-negative samples. Existing GDA techniques, such as 1 -dimensional (1D) feature masking, suffer from having a high probability of augmenting partially homogeneous views. Homogeneous views encode identical embeddings, induce substandard positive-negative samples, and enforce the performance responsibility on structural augmentation. Thus, previous work requires plenty of negative samples, converges slower, consumes more memory for training, and offers trivial performance improvements on downstream tasks. To overcome these issues, firstly , we introduce a novel 2dimensional (2D) feature masking technique in GCL to mask the feature matrix in 2 -dimensions. Secondly , we introduce heterogeneous augmentation, a combination of 1D -2D feature masking and edge dropping. Thirdly , we present a negative samples -based GCL framework: Heterogeneous D ata A ugmentation in graph Contrastive learning for E ffective N egative S amples ( DAENS ). The effectiveness of the DAENS's induced positive-negative samples can be quantified as using only inter -view negative samples improves node classification performance up to 5.84% on 8 benchmark datasets. DAENS converges faster, takes less time per epoch, and is more memory efficient than existing state-of-the-art methods. Lastly , we empirically examine the feature and structural augmentation effect on sparse and dense graphs with DAENS. The implementation of DAENS is available at https://***/mhadnanali/DAENS.

关键词： graph data augmentation graph representation learning graph contrastive learning Self-supervised learning graph machine learning

来源：评论

学校读者我要写书评

暂无评论

Sensor Networks Visualization and Analysis of the Oceanography Research Vessel Isabu

Sensor Networks Visualization and Analysis of the Oceanograp...

引用

OCEANS Hampton Roads Conference

作者： Kang, Hangoo Heo, Sang Do Lee, Gyeong-mok Jeong, Wooyoung Baeg, Saehun Kim, Daeyeon Korea Inst Ocean Sci & Technol KIOST Marine Observat Team Geoje South Korea Korea Inst Ocean Sci & Technol KIOST Instrumental Dev & Management Ctr Busan South Korea

ISBN: (数字)9781665468091

ISBN: (纸本)9781665468091

The Isabu is an oceanographic research vessel. It was launched in 2016 and is operated by KIOST. In this study, the sensor networks of the Isabu are visualized and analyzed for the derivation of meaningful information. The visualization of sensor networks was performed using Gephi which is an open-source software. The nodes and connection properties of the sensor networks were defined for visualization and analysis. The analysis of sensor networks on the Isabu was performed based on centrality analysis. In-degree, out-degree, degree centrality, closeness centrality, local clustering coefficient, and eigenvector centrality were computed. Through the results of this study, it is able to distinguish which sensors have the highest order of priority based on the quantitative figures. Therefore, the results can be used for the maintenance of research equipment on a limited budget and also be used as a basic material for graph machine learning.

关键词： sensor network network visualization network analysis graph machine learning research vessel

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：