检索结果-内蒙古大学图书馆

A network-based positive and unlabeled learning approach for fake news detection

MACHINE learning 2022年第10期111卷 3549-3592页

作者： de Souza, Mariana Caravanti Nogueira, Bruno Magalhaes Rossi, Rafael Geraldeli Marcacini, Ricardo Marcondes dos Santos, Brucce Neves Rezende, Solange Oliveira ICMC USP BR-13566590 Sao Carlos Brazil FACOM UFMS BR-79070900 Campo Grande MS Brazil CPTL UFMS BR-79613000 Tres Lagoas Brazil

Fake news can rapidly spread through internet users and can deceive a large audience. Due to those characteristics, they can have a direct impact on political and economic events. Machine learning approaches have been used to assist fake news identification. However, since the spectrum of real news is broad, hard to characterize, and expensive to label data due to the high update frequency, One-Class learning (OCL) and Positive and Unlabeled learning (PUL) emerge as an interesting approach for content-based fake news detection using a smaller set of labeled data than traditional machine learning techniques. In particular, network-based approaches are adequate for fake news detection since they allow incorporating information from different aspects of a publication to the problem modeling. In this paper, we propose a network-based approach based on Positive and Unlabeled learning by Label Propagation (PU-LP), a one-class and transductive semi-supervised learning algorithm that performs classification by first identifying potential interest and non-interest documents into unlabeled data and then propagating labels to classify the remaining unlabeled documents. A label propagation approach is then employed to classify the remaining unlabeled documents. We assessed the performance of our proposal considering homogeneous (only documents) and heterogeneous (documents and terms) networks. Our comparative analysis considered four OCL algorithms extensively employed in One-Class text classification (k-Means, k-Nearest Neighbors Density-based, One-Class Support Vector Machine, and Dense Autoencoder), and another traditional PUL algorithm (Rocchio Support Vector Machine). The algorithms were evaluated in three news collections, considering balanced and extremely unbalanced scenarios. We used Bag-of-Words and Doc2Vec models to transform news into structured data. Results indicated that PU-LP approaches are more stable and achieve better results than other PUL and OCL approaches

关键词： Fake news One-class learning Positive and unlabeled learning Transductive semi-supervised learning graph-based learning Document management Text processing

来源：评论

学校读者我要写书评

暂无评论

Joint Reconstruction-Segmentation on graphs

引用

SIAM JOURNAL ON IMAGING SCIENCES 2023年第2期16卷 911-947页

作者： Budd, Jeremy M. van Gennip, Yves Latz, Jonas Parisotto, Simone Schoenlieb, Carola-Bibiane Rhein Friedrich Wilhelms Univ Bonn Hausdorff Ctr Math Bonn Germany Delft Univ Technol Delft Inst Appl Math Delft Netherlands Heriot Watt Univ Maxwell Inst Math Sci Edinburgh Scotland Heriot Watt Univ Sch Math & Comp Sci Edinburgh Scotland Univ Cambridge Dept Appl Math & Theoret Phys Cambridge England

Practical image segmentation tasks concern images which must be reconstructed from noisy, distorted, and/or incomplete observations. A recent approach for solving such tasks is to perform this reconstruction jointly with the segmentation, using each to guide the other. However, this work has so far employed relatively simple segmentation methods, such as the Chan--Vese algorithm. In this paper, we present a method for joint reconstruction-segmentation using graph-based segmentation methods, which have been seeing increasing recent interest. Complications arise due to the large size of the matrices involved, and we show how these complications can be managed. We then analyze the convergence properties of our scheme. Finally, we apply this scheme to distorted versions of ``two cows"" images familiar from previous graph-based segmentation literature, first to a highly noised version and second to a blurred version, achieving highly accurate segmentations in both cases. We compare these results to those obtained by sequential reconstruction-segmentation approaches, finding that our method competes with, or even outperforms, those approaches in terms of reconstruction and

关键词： image reconstruction image segmentation joint reconstruction-segmentation graph-based learning Ginzburg-Landau functional Merriman--Bence--Osher scheme total variation regularization

来源：评论

学校读者我要写书评

暂无评论

Stock trend prediction based on industry relationships driven hypergraph attention networks

引用

APPLIED INTELLIGENCE 2023年第23期53卷 29448-29464页

作者： Han, Haodong Xie, Liang Chen, Shengshuang Xu, Haijiao Wuhan Univ Technol Sch Sci Wuhan 430000 Hubei Peoples R China GuangDong Univ Educ Sch Comp Sci Guangzhou 510000 Guangdong Peoples R China

In financial research, accurately predicting the movement trends of stock prices has been a focus for many researchers. The interrelationships among stocks are important factors that influence stock prices. However, recent research has revealed several limitations of traditional deep learning models in capturing these interrelationships, including the inability to learn higher-order relationships among stocks, the inability to dynamically update the relationship graph, and the failure to model the impact of industry relationships on individual stocks. To address these limitations, we propose an industry relationship-driven hypergraph attention network (IRD-HGAT) for predicting stock price movement trends. A key aspect of our work is the use of a hypergraph structure to represent the higher-order relationships among stock industries. The hypergraph attention mechanism is used to dynamically update the relationships between stocks, and the properties of industry hyperedges are aggregated to analyze the impact of industry relationships on stock prices. By comparing the current state-of-the-art algorithms, IRD-HGAT achieves excellent predictive performance and profitability on both S &P500 and CSi500 datasets, with AUC and Sharpe ratios of 0.87 and 1.12, respectively. Ablation experiments and parameter sensitivity analyses also further validate the validity and predictive stability of the model components.

关键词： Stock prediction graph-based learning Attribute aggregation Quantitative investments

来源：评论

学校读者我要写书评

暂无评论

Cross-GCN: Enhancing graph Convolutional Network with k-Order Feature Interactions

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2023年第1期35卷 225-236页

作者： Feng, Fuli He, Xiangnan Zhang, Hanwang Chua, Tat-Seng Nanyang Technol Univ Sch Comp Sci & Engn Sea NExT Joint Lab Singapore 117417 Singapore Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230052 Anhui Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore

graph Convolutional Network (GCN) is an emerging technique that performs learning and reasoning on graph data. It operates feature learning on the graph structure, through aggregating the features of the neighbor nodes to obtain the embedding of each target node. Owing to the strong representation power, recent research shows that GCN achieves state-of-the-art performance on several tasks such as recommendation and linked document classification. Despite its effectiveness, we argue that existing designs of GCN forgo modeling cross features, making GCN less effective for tasks or data where cross features are important. Although neural network can approximate any continuous function, including the multiplication operator for modeling feature crosses, it can be rather inefficient to do so (i.e., wasting many parameters at the risk of overfitting) if there is no explicit design. To this end, we design a new operator named Cross-feature graph Convolution, which explicitly models the arbitrary-order cross features with complexity linear to feature dimension and order size. We term our proposed architecture as Cross-GCN, and conduct experiments on three graphs to validate its effectiveness. Extensive analysis validates the utility of explicitly modeling cross features in GCN, especially for feature learning at lower layers.

关键词： Cross-feature graph-based learning graph neural networks

来源：评论

学校读者我要写书评

暂无评论

FLAG: Faster learning on Anchor graph with Label Predictor Optimization

引用

IEEE TRANSACTIONS ON BIG DATA 2022年第3期8卷 579-591页

作者： Fu, Weijie Wang, Meng Hao, Shijie Mu, Tingting Hefei Univ Technol Sch Comp & Informat Hefei 230009 Anhui Sheng Peoples R China Univ Manchester Sch Comp Sci Manchester M13 9PL Lancs England

Knowledge graphs have received intensive research interests. When the labels of most nodes or datapoints are missing, anchor graph and hierarchical anchor graph models can be employed. With an anchor graph or hierarchical anchor graph, we only need to optimize the labels of the coarsest anchors, and the labels of datapoints can be inferred from these anchors in a coarse-to-fine manner. The complexity of optimization is therefore reduced to a cubic cost with respect to the number of the coarsest anchors. However, to obtain a high accuracy when a data distribution is complex, the scale of this anchor set still needs to be large, which thus inevitably incurs an expensive computational burden. As such, a challenge in scaling up these models is how to efficiently estimate the labels of these anchors while keeping classification performance. To address this problem, we propose a novel approach that adds an anchor label predictor in the conventional anchor graph and hierarchical anchor graph models. In the proposed approach, the labels of the coarsest anchors are not directly optimized, and instead, we learn a label predictor which estimates the labels of these anchors with their spectral representations. The predictor is optimized with a regularization on all datapoints based on a hierarchical anchor graph, and we show that its solution only involves the inversion of a small-size matrix. Built upon the anchor hierarchy, we design a sparse intra-layer adjacency matrix over these anchors, which can simultaneously accelerate spectral embedding and enhance effectiveness. Our approach is named Faster learning on Anchor graph (FLAG) as it improves conventional anchor-graph-based methods in terms of efficiency. Experiments on a variety of publicly available datasets with sizes varying from thousands to millions of samples demonstrate the effectiveness of our approach.

关键词： Optimization Computational modeling Big Data Sparse matrices Computational efficiency Approximation algorithms Complexity theory Semi-supervised learning graph-based learning machine learning

来源：评论

学校读者我要写书评

暂无评论

Local and Global Spatial Information for Land Cover Semisupervised Classification of Complex Polarimetric SAR Data

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2023年 16卷 3892-3904页

作者： Ghanbari, Mohsen Xu, Linlin Clausi, David A. Univ Waterloo Dept Syst Design Engn Vis & Image Proc VIP Res Grp Waterloo ON N2L 3G1 Canada

Each of the three satellites constituting the RADARSAT Constellation Mission (RCM) provides compact polarimetric synthetic aperture radar (CP SAR) data. The complex CP data have similar properties to the complex quad polarimetric (QP) data provided by prior RADARSAT missions. In this article, a land cover classification method using spatial information is designed based on the statistical characteristics of the complex CP and QP SAR data. First, the local spatial dependency among pixels is captured by superpixels. Second, a graph is constructed on the superpixels to model the global spatial dependency among superpixels. The land cover classification image with land cover type labels is then estimated by propagating labels from the few labeled superpixels to the unlabeled superpixels. Classification of two RCM complex CP and QP scenes demonstrates that the proposed method, with few labeled pixels, provides much higher classification accuracy than methods that do not exploit global spatial dependency.

关键词： Synthetic aperture radar Convolutional neural networks Backscatter Satellites Covariance matrices Classification algorithms Radar polarimetry Compact polarimetry graph-based learning land cover classification multilook complex semisupervised superpixel

来源：评论

学校读者我要写书评

暂无评论

Use of Knowledge graphs for Construction Safety Management: A Systematic Literature Review

引用

INFORMATION 2024年第7期15卷 390-390页

作者： Kong, Fansheng Ahn, Seungjun Hongik Univ Dept Civil & Environm Engn Seoul 04066 South Korea

Effective safety management is crucial in the construction industry. The growing interest in employing Knowledge graphs (KGs) for safety management in construction is driven by the need for efficient computing-aided safety practices. This paper systematically reviews the literature related to automating safety management processes through knowledge base systems, focusing on the creation and utilization of KGs for construction safety. It captures current methodologies for developing and using KGs in construction safety management, outlining the techniques for each phase of KG development, including scope identification, integration of external data, ontological modeling, data extraction, and KG completion. This provides structured guidance on building a KG for safety management. Moreover, this paper discusses the challenges and limitations that hinder the wider adoption of KGs in construction safety management, leading to the identification of goals and considerations for future research.

关键词： knowledge graph construction safety management ontology graph-based learning text mining

来源：评论

学校读者我要写书评

暂无评论

Quantitative stock portfolio optimization by multi-task learning risk and return

引用

INFORMATION FUSION 2024年 104卷

作者： Ma, Yu Mao, Rui Lin, Qika Wu, Peng Cambria, Erik Nanjing Univ Sci & Technol Sch Econ & Management 200 Xiaolingwei Rd Nanjing 210094 Jiangsu Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn 50 Nanyang Ave Singapore 639798 Singapore Xi An Jiao Tong Univ Sch Comp Sci & Technol Xian 710049 Shaanxi Peoples R China Nanjing Univ Sci & Technol Sch Intelligent Mfg 200 Xiaolingwei Rd Nanjing 210094 Jiangsu Peoples R China

Selecting profitable stocks for investments is a challenging task. Recent research has made significant progress on stock ranking prediction to select top-ranked stocks for portfolio optimization. However, the stocks are only ranked by predicted stock return, ignoring the stock price volatility risk - a critical aspect for stock selection and investments. Moreover, they preliminarily attempted to capture the effects of related stocks from a singular relation, disregarding the rich information regarding multiple spillover effects from related stocks and the distinctions in effects among various relations. Thus, we propose a risk and return multitask learning model with a heterogeneous graph attention network (HGA-MT) to predict stock ranking for portfolio optimization. First, to aggregate the multiple spillover effects of related stocks, we introduce graph convolutional networks to fuse the effects of related stocks in each relation and design an attention network to allocate varying weights to different types of relationships. Second, we use a multi-task learning paradigm to learn stock return and volatility risks jointly. The stock ranking results are calculated by simultaneously considering the risk and return. Thus, Top -K ranked stocks are recommended in the portfolio for the next trading day to achieve higher and more stable profits. Extensive experiments prove that HGA-MT outperforms previous state-of-the-art methods in stock ranking and backtesting trading evaluation tasks.

关键词： Stock portfolio optimization Quantitative stock selection Multi-task learning Stock relation graph graph-based learning

来源：评论

学校读者我要写书评

暂无评论

Modeling EEG Data into graphs for the Prognostic of Patients in Coma Using graph Neural Networks 34th

Modeling EEG Data into Graphs for the Prognostic of Patients...

引用

34th Brazilian Conference on Intelligent Systems

作者： Nascimento Junior, Odelmo O. Assis, Dhara L. C. Destro Filho, Joao B. Zhao, Liang Carneiro, Murillo G. Univ Fed Uberlandia Fac Comp Uberlandia MG Brazil Univ Sao Paulo Dept Comp & Math Ribeirao Preto Brazil

ISBN: (纸本)9783031790379;9783031790386

In this work we present a modeling approach using graph Neural Networks (GNNs) to support the prognosis of patients in coma (PPC) based on Electroencephalogram (EEG) exams. Coma is a critical medical condition characterized by an extended state of unconsciousness. EEG is an exam that captures the electrical activity of the brain through electrodes positioned on the patient's scalp. It provides valuable information about cerebral functions and can also be used for the monitoring and diagnosis of several diseases. In this study, we investigate four GNN architectures specifically designed for PPC analysis, leveraging the power of convolutional-based layers. In addition, we also develop a modeling strategy to represent EEG sequential data into a graph, named EEgraph, effectively harnessing the spatial positions of electrodes. The main contribution of representing the EEG exam in a graph structure is also to explore all the inherent spatial information the exam has. As it is a highly sensitive exam with generally noisy results on the microvolt scale, its spatial exploration may reveal the potential to improve the PPC task. Experimental results considering real data showed that our proposed architecture outperformed the LSTM model in terms of F1-score and accuracy. Statistical tests evidenced the enhanced predictive performance achieved by exploiting the spatial aspects of EEG data using GNNs. Moreover, the findings highlight the significant potential of GNNs to contribute to the PPC task from EEG data.

关键词： graph Neural Networks Electroencephalogram Coma outcome Sequential data graph-based learning EEgraph

来源：评论

学校读者我要写书评

暂无评论

LIPSCHITZ REGULARITY OF graph LAPLACIANS ON RANDOM DATA CLOUDS

引用

SIAM JOURNAL ON MATHEMATICAL ANALYSIS 2022年第1期54卷 1169-1222页

作者： Calder, Jeff Trillos, Nicolas Garcia Lewicka, Marta Univ Minnesota Sch Math Minneapolis MN 55455 USA Univ Wisconsin Dept Stat Madison WI 53706 USA Univ Pittsburgh Dept Math Pittsburgh PA 15260 USA

In this paper we study Lipschitz regularity of elliptic PDEs on geometric graphs, constructed from random data points. The data points are sampled from a distribution supported on a smooth manifold. The family of equations that we study arises in data analysis in the context of graph-based learning and contains, as important examples, the equations satisfied by graph Laplacian eigenvectors. In particular, we prove high probability interior and global Lipschitz estimates for solutions of graph Poisson equations. Our results can be used to show that graph Laplacian eigenvectors are, with high probability, essentially Lipschitz regular with constants depending explicitly on their corresponding eigenvalues. Our analysis relies on a probabilistic coupling argument of suitable random walks at the continuum level, and an interpolation method for extending functions on random point clouds to the continuum manifold. As a byproduct of our general regularity results, we obtain high probability L-infinity and approximate C-0,C-1 convergence rates for the convergence of graph Laplacian eigenvectors toward eigenfunctions of the corresponding weighted Laplace-Beltrami operators. The convergence rates we obtain scale like the L-2 convergence rates established in J. Calder and N. Garcia Trillos, arXiv:1910.13476, 2019.

关键词： graph Laplacian random data cloud graph-based learning

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：