检索结果-内蒙古大学图书馆

Clustering Enhanced Multiplex graph Contrastive representation learning

IEEE TRANSACTIONS ON NEURAL NETWORKS AND learning SYSTEMS 2025年第1期36卷 1341-1355页

作者： Yuan, Ruiwen Tang, Yongqiang Wu, Yajing Zhang, Wensheng Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 101408 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence Beijing 100190 Peoples R China Guangzhou Univ Sch Comp Sci & Cyber Engn Guangzhou 510006 Peoples R China

Multiplex graph representation learning has attracted considerable attention due to its powerful capacity to depict multiple relation types between nodes. Previous methods generally learn representations of each relation-based subgraph and then aggregate them into final representations. Despite the enormous success, they commonly encounter two challenges: 1) the latent community structure is overlooked and 2) consistent and complementary information across relation types remains largely unexplored. To address these issues, we propose a clustering-enhanced multiplex graph contrastive representation learning model (CEMR). In CEMR, by formulating each relation type as a view, we propose a multiview graph clustering framework to discover the potential community structure, which promotes representations to incorporate global semantic correlations. Moreover, under the proposed multiview clustering framework, we develop cross-view contrastive learning and cross-view cosupervision modules to explore consistent and complementary information in different views, respectively. Specifically, the cross-view contrastive learning module equipped with a novel negative pairs selecting mechanism enables the view-specific representations to extract common knowledge across views. The cross-view cosupervision module exploits the high-confidence complementary information in one view to guide low-confidence clustering in other views by contrastive learning. Comprehensive experiments on four datasets confirm the superiority of our CEMR when compared to the state-of-the-art rivals.

关键词： Multiplexing representation learning Semantics Feature extraction Correlation Training Task analysis Contrastive learning graph representation learning multiplex graph multiview graph clustering

来源：评论

学校读者我要写书评

暂无评论

GRLGRN: graph representation-based learning to infer gene regulatory networks from single-cell RNA-seq data

引用

BMC BIOINFORMATICS 2025年第1期26卷 1-19页

作者： Wang, Kai Li, Yulong Liu, Fei Luan, Xiaoli Wang, Xinglong Zhou, Jingwen Jiangnan Univ Sch Internet Things Engn Key Lab Adv Proc Control Light Ind Minist Educ Lihu Rd 1800 Wuxi 214122 Jiangsu Peoples R China Jiangnan Univ Sci Ctr Future Foods 1800 Lihu Rd Wuxi 214122 Jiangsu Peoples R China Jiangnan Univ Sch Biotechnol Key Lab Ind Biotechnol Minist Educ 1800 Lihu Rd Wuxi 214122 Jiangsu Peoples R China Jiangnan Univ Engn Res Ctr Minist Educ Food Synthet Biotechnol 1800 Lihu Rd Wuxi 214122 Jiangsu Peoples R China Jiangnan Univ Jiangsu Prov Engn Res Ctr Food Synthet Biotechnol 1800 Lihu Rd Wuxi 214122 Jiangsu Peoples R China

BackgroundA gene regulatory network (GRN) is a graph-level representation that describes the regulatory relationships between transcription factors and target genes in cells. The reconstruction of GRNs can help investigate cellular dynamics, drug design, and metabolic systems, and the rapid development of single-cell RNA sequencing (scRNA-seq) technology provides important opportunities while posing significant challenges for reconstructing GRNs. A number of methods for inferring GRNs have been proposed in recent years based on traditional machine learning and deep learning algorithms. However, inferring the GRN from scRNA-seq data remains challenging owing to cellular heterogeneity, measurement noise, and data *** this study, we propose a deep learning model called graph representational learning GRN (GRLGRN) to infer the latent regulatory dependencies between genes based on a prior GRN and data on the profiles of single-cell gene expressions. GRLGRN uses a graph transformer network to extract implicit links from the prior GRN, and encodes the features of genes by using both an adjacency matrix of implicit links and a matrix of the profile of gene expression. Moreover, it uses attention mechanisms to improve feature extraction, and feeds the refined gene embeddings into an output module to infer gene regulatory relationships. To evaluate the performance of GRLGRN, we compared it with prevalent models and performed ablation experiments on seven cell-line datasets with three ground-truth networks. The results showed that GRLGRN achieved the best predictions in AUROC and AUPRC on 78.6% and 80.9% of the datasets, and achieved an average improvement of 7.3% in AUROC and 30.7% in AUPRC. The interpretation discussion and the network visualization were *** experimental results and case studies illustrate the considerable performance of GRLGRN in predicting gene interactions and provide interpretability for the prediction tasks, such as id

关键词： Gene regulatory network Gene expression data graph representation learning Implicit links

来源：评论

学校读者我要写书评

暂无评论

graph representation learning for Similarity Stocks Analysis

引用

JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY 2022年第11期94卷 1283-1292页

作者： Zhang, Boyao Yang, Chao Zhang, Haikuo Wang, Zongguo Sun, Jingqi Wang, Lihua Zhao, Yonghua Wang, Yangang Chinese Acad Sci Comp Network Informat Ctr Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Beijing Univ Aeronaut & Astronaut Coll Software Beijing Peoples R China China Internet Network Informat Ctr Beijing Peoples R China

Listed companies with similar or related fundamentals usually influence each other, and these influences are usually reflected in stock prices. For example, the momentum spillover effect in the behavioral finance theory describes the formation of lead-lag effects between the stock prices of related companies. The relationship between listed companies consists of many types, such as relationships in the industry chain, industry information, transaction information, patent sharing degree, equity, etc. We construct a set of industry chain knowledge graph of listed companies to describe the production and supply relationship between the upstream and downstream of listed companies. Then, graph representation learning method is used to study the relevance between listed company entities in the knowledge graph. It includes dimensions such as industry and transaction information of listed companies as weights to optimize the graph representation learning process, and finally calculates the similarity index between listed companies. To evaluate the effectiveness of the method, we conduct a link prediction experiment and construct a stock quantitative investment portfolio based on the similarity index. The result of the quantitative backtest experiment based on China's stock market data in the last 10 years shows that the graph representation learning method we proposed can be used to study the momentum spillover effect and obtain investment returns.

关键词： Industrial chain knowledge graph graph representation learning Similarity stock analysis Momentum spillover effects

来源：评论

学校读者我要写书评

暂无评论

graph representation learning Based on Cognitive Spreading Activations

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第12期36卷 8408-8420页

作者： Bai, Jie Zhao, Kang Li, Linjing Zeng, Daniel Li, Qiudan Yang, Fan Zu, Quannan Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence S Beijing 100190 Peoples R China Univ Iowa Tippie Coll Business Iowa City IA 52242 USA Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100190 Peoples R China Tianjin Univ Coll Management & Econ Tianjin 300072 Peoples R China

graph representation learning is an emerging area for graph analysis and inference. However, existing approaches for large-scale graphs either sample nodes in sequential walks or manipulate the adjacency matrices of graphs. The former approach can cause sampling bias against less-connected nodes, whereas the latter may suffer from sparsity that exists in many real-world graphs. To learn from structural information in a graph more efficiently and comprehensively, this paper proposes a new graph representation learning approach inspired by the cognitive model of spreading-activation mechanisms in human memory. This approach learns node embeddings by adopting a graph activation model that allows nodes to "activate" their neighbors and spread their own structural information to other nodes through the paths simultaneously. Comprehensive experiments demonstrate that the proposed model performs better than existing methods on several empirical datasets for multiple graph inference tasks. Meanwhile, the spreading-activation-based model is computationally more efficient than existing approaches-the training process converges after only a small number of iterations, and the training time is linear in the number of edges in a graph. The proposed method works for both homogeneous and heterogeneous graphs.

关键词： representation learning Social networking (online) Vectors Analytical models Training Task analysis Computational modeling Cognitive psychology graph analysis graph embedding graph representation learning structural analysis

来源：评论

学校读者我要写书评

暂无评论

graph representation learning Enhanced Semi-Supervised Feature Selection

引用

ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA 2024年第9期18卷 1-20页

作者： Tan, Jun Qi, Zhifeng Gui, Ning Cent South Univ Sch Comp Sci & Engn Changsha Peoples R China Cent South Univ Sch Automat Changsha Peoples R China

Feature selection is a key step in machine learning by eliminating features that are not related to the modeling target to create reliable and interpretable models. By exploring the potential complex correlations among features of unlabeled data, recently introduced self-supervision-enhanced feature selection greatly reduces the reliance on the labeled samples. However, they are generally based on the autoencoder with sample-wise self-supervision, which can hardly exploit the relations among samples. To address this limitation, this article proposes graph representation learning enhanced semi-supervised feature selection (G-FS) which performs feature selection based on the discovery and exploitation of the non-Euclidean relations among features and samples by translating unlabeled "plain" tabular data into a bipartite graph. A self-supervised edge prediction task is designed to distill rich information on the graph into low-dimensional embeddings, which remove redundant features and noise. Guided by the condensed graph representation, we propose a batch attention feature weight generation mechanism that generates more robust weights according to batch-based selection patterns rather than individual samples. The results show that G-FS achieves significant performance edges in 14 datasets compared to twelve state-of-the-art baselines, including two recent self-supervised baselines. The source code is public available at https://***/Icannotnamemyselff/G-FS_graph_enhacned_feature_ selection.

关键词： feature selection method semi-supervised learning graph representation learning

来源：评论

学校读者我要写书评

暂无评论

graph representation learning With Adaptive Metric

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2023年第4期10卷 2074-2085页

作者： Zhang, Chun-Yang Cai, Hai-Chun Chen, C. L. Philip Lin, Yue-Na Fang, Wu-Peng Fuzhou Univ Sch Comp & Data Sci Fuzhou 350025 Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China

Contrastive learning has been widely used in graph representation learning, which extracts node or graph representations by contrasting positive and negative node pairs. It requires node representations (embeddings) to reflect their correlations in topology, increasing the similarities between an anchor node and its positive nodes, or reducing the similarities with its negative nodes in embedding space. However, most existing contrastive models measure similarities through a fixed metric that equally scores all sample pairs in a specific feature space, but ignores the varieties of node attributes and network topologies. Moreover, these fixed metrics are always defined explicitly and manually, which makes them unsuitable for applying to all graphs and networks. To solve these problems, we propose a novel graph representation learning model with an adaptive metric, called GRAM, which produces appropriate similarity scores of node pairs according to the different significance of each dimension in their embedding vectors and adaptive metrics based on data distribution. With these scores, it is better to train a graph encoder and obtain representative embeddings. Experimental results show that GRAM has strong competitiveness in multiple tasks.

关键词： Adaptive metric contrastive learning graph representation learning metric learning

来源：评论

学校读者我要写书评

暂无评论

graph representation learning via simple jumping knowledge networks

引用

APPLIED INTELLIGENCE 2022年第10期52卷 11324-11342页

作者： Yang, Fei Zhang, Huyin Tao, Shiming Hao, Sheng Wuhan Univ Sch Comp Sci Wuhan Peoples R China Minist Nat Resources Key Lab Urban Land Resources Monitoring & Simulat Shenzhen Peoples R China Cent China Normal Univ Sch Comp Sci Wuhan Peoples R China

Recent graph neural networks for graph representation learning depend on a neighborhood aggregation process. Several works focus on simplifying the neighborhood aggregation process and model structures. However, as the depth of the models increases, the simplified models will encounter oversmoothing, resulting in a decrease in model performance. Several works leverage sophisticated learnable neighborhood aggregation algorithms to learn more accurate graph representations. However, the high computational cost limits the depth of these models and the ability to tackle large graphs. In this paper, we propose simple jumping knowledge networks (SJK-Nets), which first leverage a simple no-learning method to complete the neighborhood aggregation process, and then utilize a jumping architecture to combine the different neighborhood ranges of each node to achieve a better structure-aware representation. Under such circumstances, first, we use a simple neighborhood aggregation algorithm to reduce computational complexity of the model. Then, we aggregate the features of high-order neighboring nodes to learn more informative node feature representations. Finally, by combining the above methods, the oversmoothing problem of the deep graph neural networks is alleviated. Our experimental evaluation demonstrates that SJK-Nets achieve or match state-of-the-art results in node classification tasks, text classification tasks, and community prediction tasks. Moreover, since SJK-Nets' neighborhood aggregation is a no-learning process, SJK-Nets are successfully extended to node clustering tasks.

关键词： graph neural networks graph representation learning Neighborhood aggregation Simple jumping knowledge networks No-learning

来源：评论

学校读者我要写书评

暂无评论

graph representation learning Beyond Node and Homophily

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2023年第5期35卷 4880-4893页

作者： Li, You Lin, Bei Luo, Binli Gui, Ning Cent South Univ Sch Comp Sci & Engn Changsha 410083 Hunan Peoples R China

Unsupervised graph representation learning aims to distill various graph information into a downstream task-agnostic dense vector embedding. However, existing graph representation learning approaches are designed mainly under the node homophily assumption: connected nodes tend to have similar labels and optimize performance on node-centric downstream tasks. Their design is apparently against the task-agnostic principle and generally suffers poor performance in tasks, e.g., edge classification, that demands feature signals beyond the node-view and homophily assumption. To condense different feature signals into the embeddings, this paper proposes PairE, a novel unsupervised graph embedding method using two paired nodes as the basic unit of embedding to retain the high-frequency signals between nodes to support node-related and edge-related tasks. Accordingly, a multi-self-supervised autoencoder is designed to fulfill two pretext tasks: one retains the high-frequency signal better, and another enhances the representation of commonality. Our extensive experiments on a diversity of benchmark datasets clearly show that PairE outperforms the unsupervised state-of-the-art baselines, with up to 101.1% relative improvement on the edge classification tasks that rely on both the high and low-frequency signals in the pair and up to 82.5% relative performance gain on the node classification tasks.

关键词： Task analysis representation learning Performance gain Benchmark testing Training Topology Semisupervised learning graph representation learning homophily and heterophily network low and high-frequency signals self-supervised autoencoder

来源：评论

学校读者我要写书评

暂无评论

graph representation learning based on deep generative gaussian mixture models

引用

NEUROCOMPUTING 2023年 523卷 157-169页

作者： Niknam, Ghazaleh Molaei, Soheila Zare, Hadi Clifton, David Pan, Shirui Univ Tehran Fac New Sci & Technol Tehran Iran Univ Oxford Dept Engn Sci Oxford England Griffith Univ Sch Informat & Commun Technol Brisbane Australia Oxford Suzhou Ctr Adv Res OSCAR Suzhou Peoples R China

graph representation learning is an effective tool for facilitating graph analysis with machine learning methods. Most GNNs, including graph Convolutional Networks (GCN), graph Recurrent Neural Networks (GRNN), and graph Auto-Encoders (GAE), employ vectors to represent nodes in a deterministic way without exploiting the uncertainty in hidden variables. Deep generative models are combined with GAE in the Variational graph Auto-Encoder (VGAE) framework to address this issue. While traditional VGAE-based methods can capture hidden and hierarchical dependencies in latent spaces, they are limited by the data's multimodality. Here, we propose the Gaussian Mixture Model (GMM) to model the prior distribution in VGAE. Furthermore, an adversarial regularization is incorporated into the proposed approach to ensure the fruitful impact of the latent representations on the results. We demonstrate the performance of the proposed method on clustering and link prediction tasks. Our experimental results on real datasets show remarkable performance compared to state-of-the-art methods.(c) 2022 Elsevier B.V. All rights reserved.

关键词： graph representation learning Node embedding Variational graph auto -encoder Adversarial mechanism Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

graph representation learning Based on Specific Subgraphs for Biomedical Interaction Prediction

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2024年第5期21卷 1552-1564页

作者： Pang, Huaxin Wei, Shikui Du, Zhuoran Zhao, Yufeng Cai, Shengxing Zhao, Yao Beijing Jiaotong Univ Sch Comp Informat Technol Beijing 100044 Peoples R China Beijing Key Lab Adv Informat Sci Network Technol Beijing 100044 Peoples R China China Acad Chinese Med Sci Natl Data Ctr Tradit Chinese Med Beijing 100010 Peoples R China

Discovering the novel associations of biomedical entities is of great significance and can facilitate not only the identification of network biomarkers of disease but also the search for putative drug targets. graph representation learning (GRL) has incredible potential to efficiently predict the interactions from biomedical networks by modeling the robust representation for each node.> However, the current GRL-based methods learn the representation of nodes by aggregating the features of their neighbors with equal weights. Furthermore, they also fail to identify which features of higher-order neighbors are integrated into the representation of the central node. In this work, we propose a novel graph representation learning framework: a multi-order graph neural network based on reconstructed specific subgraphs (MGRS) for biomedical interaction prediction. In the MGRS, we apply the multi-order graph aggregation module (MOGA) to learn the wide-view representation by integrating the multi-hop neighbor features. Besides, we propose a subgraph selection module (SGSM) to reconstruct the specific subgraph with adaptive edge weights for each node. SGSM can clearly explore the dependency of the node representation on the neighbor features and learn the subgraph-based representation based on the reconstructed weighted subgraphs. Extensive experimental results on four public biomedical networks demonstrate that the MGRS performs better and is more robust than the latest baselines.

关键词： graph representation learning biomedical networks link prediction modeling subgraph

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：