检索结果-内蒙古大学图书馆

GRELA: Exploiting graph representation learning in effective approximate query processing

VLDB JOURNAL 2025年第3期34卷 1-26页

作者： Li, Pengfei Zhang, Yong Wei, Wenqing Zhu, Rong Ding, Bolin Zhou, Jingren Hu, Shuxian Lu, Hua Roskilde Univ Roskilde Denmark Baidu Beijing Peoples R China USTC Hefei Peoples R China Alibaba Grp Hangzhou Peoples R China Aalborg Univ Copenhagen Denmark

Approximate query processing (AQP) plays a critical role in modern data analytics. Although machine learning models are used for AQP, existing methods fail to uncover implicit relationships among the underlying data, the aggregate functions in queries, and the query predicates. In this work, we propose a graph representation learning-based AQP model (GRELA for short) for answering queries with multiple aggregate functions. GRELA models the aggregate functions and the query predicates as task and clause nodes respectively in a graph and then learns appropriate node representations via its two modules. In particular, the Encoder\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\texttt {Encoder}$$\end{document} module coalesces query predicates and underlying data into the representations of clause nodes. The graph\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathbf {\texttt {graph}}$$\end{document} module bridges task nodes and clause nodes such that each task node can aggregate the information from its neighborhood into its representation. Through the inner products of clause and task representations, GRELA is able to make accurate estimates for queries with multiple aggregate functions. Extensive experimental results verify that GRELA outperforms the state-of-the-art AQP methods on different kinds of datasets.

关键词： AQP graph representation learning

来源：评论

学校读者我要写书评

暂无评论

Robust graph representation learning with asymmetric debiased contrasts

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 269卷

作者： Li, Wen Ng, Wing W. Y. Wang, Hengyou Zhang, Jianjun Zhong, Cankun South China Univ Technol Sch Comp Sci & Engineer Guangdong Prov Key Lab Computat Intelligence & Cyb Guangzhou 51006 Peoples R China South China Agr Univ Coll Math & Informat Guangzhou 510642 Peoples R China Beijing Univ Civil Engn & Architecture Sch Sci Beijing 100044 Peoples R China

The use of adversarial learning to create augmented nodes for graph Contrastive learning (GCL) aims to enhance the robustness of GCL. However, it may also lead to a change of the adversarial node's identity which degrades the performance of GCL. Therefore, Robust graph representation learning with Asymmetric Debiased Contrasts (AD-RGCL) is proposed to enhance both performance and robustness in this work. On the one hand, an asymmetric contrastive function is introduced to weaken the influence of the adversarial view. On the other hand, a weighted debiased process is carried out to remove false negative nodes via an estimation of the distribution of negative nodes and assign larger contrastive weights to true negative nodes to push them away from target nodes. Finally, anew asymmetric debiased loss is proposed for AD-RGCL based on the aforementioned asymmetric contrastive function and weighted debiased negative contrast. Experimental results on six datasets show that AD-RGCL yields better performance on node classification tasks in comparison to state-of-the-art methods. Further experiments show that AD-RGCL is robust to adversarial attacks.

关键词： graph contrastive learning graph representation learning Adversarial training Debiased contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Distributed On-Demand Routing Algorithm With graph representation learning for Industrial IoT

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2025年第1期12卷 332-343页

作者： Dai, Bin Li, Hetao Huang, Wenrui Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China

Emerging industrial Internet-of-Things (IoT) applications demand diverse and critical Quality of Service (QoS). Deep reinforcement learning (DRL)-based routing approaches offer promise but struggle with scalability and convergence, particularly when dealing with graph-based network information. To tackle the challenge, we propose a distributed routing model that leverages graph representation learning (GRL) to learn the optimal routing decision in a distributed manner. We further present on-demand routing algorithms composed of graph representation learning (GRL)-based feature engineering and DRL-based routing decision-making to meet differential QoS requirements. Experimental results demonstrate our approach outperforms state-of-the-art DRL-based routing algorithms in a distributed manner, particularly in large-scale and heavy-load networks.

关键词： Routing Quality of service Scalability Industrial Internet of Things Network topology Delays Vectors Topology representation learning Heuristic algorithms graph representation learning quality of service deep reinforcement learning routing optimization industrial Internet-of-Things

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous graph representation learning via mutual information estimation for fraud detection

引用

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS 2025年 234卷

作者： Zhang, Zheng Su, Xiangyu Wu, Ji Tessone, Claudio J. Liao, Hao Nanyang Inst Technol Sch Comp & Software Nanyang 473004 Peoples R China Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Nanyang Educ Informatizat Engn Technol Res Ctr Nanyang 473004 Peoples R China Univ Zurich UZH Blockchain Ctr CH-8050 Zurich Switzerland Univ Zurich URPP Social Networks Zurich Switzerland

In the fraud detection, fraudsters frequently engage with numerous benign users to disguise their activities. Consequently, the fraud graph exhibits not only homogeneous connections between the fraudsters and the same labeled nodes, but also heterogeneous connections, where fraudsters interact with the legitimate nodes. Heterogeneous graph representation learning aims at extracting the structural and semantic information and embed it into the low-dimensional node representation. Recently, maximizing the mutual information between the local node embedding and the summary representation has achieved the promising results on node classification tasks. However, existing deep graph infomax methods still have the following limitations. Firstly, attribute information of nodes in the graph is not fully utilized for capturing the semantic relationships between nodes. Secondly, the local and global supervision signal are not simultaneously exploited for the node embedding learning. Thirdly, the multiplex heterogeneous relations among nodes are ignored. To address these issues, a heterogeneous graph representation learning model by mutual information estimation (MIE-HetGRL) is proposed in this paper to identify the fraudsters in the fraud review graph. Concretely, a high-order mutual information estimation is proposed to integrate the local and global mutual information as the supervision signal. Then we devise a semantic attention fusion module to aggregate the relation-aware node embeddings into a compact node representation. Finally, a joint contrastive learning is designed for facilitating the training and optimization of model. The experimental results show that our proposed model significantly outperforms state-of-the-art baselines for fraud detection.

关键词： Heterogeneous graph Neural networks graph representation learning Mutual information Fraud detection

来源：评论

学校读者我要写书评

暂无评论

GRL-ITransformer: An Intelligent Method for Multi-Wind-Turbine Wake Analysis Based on graph representation learning With Improved Transformer

引用

IEEE ACCESS 2025年 13卷 43572-43592页

作者： Han, Kang Xu, Li Shanghai Univ Elect Power Coll Math & Phys Shanghai 200090 Peoples R China

The importance of examining the wake effect of wind farms for optimizing their layout and augmenting their power generation efficiency is immense. Considering that the establishment of extensive wind farms often leads to a significant number of turbines being positioned downstream of preceding ones, it significantly diminishes their power generation efficiency. In our study, we propose a graph representation learning model with improved Transformer (GRL-ITransformer) to better integrate feature information, so that the model can capture the dynamic time relationship of different variables and establish its spatial relationship, striving to enhance the precision in predicting wind turbine wake field. Different from the previous way involving handling reduced-order and separating prediction process, we combine the reduced-order technique with the proposed model to make the model more efficiently and intelligently determine the number of modes required for model prediction. After that, the data driven method is employed to update the parameters, and the superiority of GRL-ITransformer is highlighted by analyzing and comparing with the existing five classical intelligent algorithms (belongs to four categories). The comprehensive results show that GRL-ITransformer has excellent performance in wind turbine wake field prediction and reconstruction, and always possesses the lowest error for a series of error evaluation indexes among all models.

关键词： Wind turbines Predictive models Transformers Wind farms Prediction algorithms representation learning Neural networks Wind speed Data models Accuracy Wind turbine wakes reduced-order model improved transformer attention mechanism graph representation learning series forecasting algorithm

来源：评论

学校读者我要写书评

暂无评论

HeteroSample: Meta-Path Guided Sampling for Heterogeneous graph representation learning

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第4期12卷 4390-4402页

作者： Liu, Ao Chen, Jing Du, Ruiying Wu, Cong Feng, Yebo Li, Teng Ma, Jianfeng Wuhan Univ Sch Cyber Sci & Engn Key Lab Aerosp Informat Secur & Trusted Comp Minist Educ Wuhan 430072 Peoples R China Wuhan Univ Rizhao Inst Informat Technol Wuhan 430072 Peoples R China Wuhan Univ Collaborat Innovat Ctr Geospatial Technol Wuhan 430072 Peoples R China Nanyang Technol Univ Coll Comp & Data Sci Singapore 639798 Singapore Xidian Univ Sch Cyber Engn Xian 710071 Peoples R China

The rapid expansion of Internet of Things (IoT) has resulted in vast, heterogeneous graphs that capture complex interactions among devices, sensors, and systems. Efficient analysis of these graphs is critical for deriving insights in IoT scenarios, such as smart cities, industrial IoT, and intelligent transportation systems. However, the scale and diversity of IoT-generated data present significant challenges, and existing methods often struggle with preserving the structural integrity and semantic richness of these complex graphs. Many current approaches fail to maintain the balance between computational efficiency and the quality of the insights generated, leading to potential loss of critical information necessary for accurate decision-making in IoT applications. We introduce HeteroSample, a novel sampling method designed to address these challenges by preserving the structural integrity, node and edge type distributions, and semantic patterns of IoT-related graphs. HeteroSample works by incorporating the novel top-leader selection, balanced neighborhood expansion, and meta-path guided sampling strategies. The key idea is to leverage the inherent heterogeneous structure and semantic relationships encoded by meta-paths to guide the sampling process. This approach ensures that the resulting subgraphs are representative of the original data while significantly reducing computational overhead. Extensive experiments demonstrate that HeteroSample outperforms state-of-the-art methods, achieving up to 15% higher F1 scores in tasks, such as link prediction and node classification, while reducing runtime by 20%. These advantages make HeteroSample a transformative tool for scalable and accurate IoT applications, enabling more effective and efficient analysis of complex IoT systems, ultimately driving advancements in smart cities, industrial IoT, and beyond.

关键词： graph representation learning graph sampling heterogeneous graphs node embedding graph representation learning graph sampling heterogeneous graphs node embedding

来源：评论

学校读者我要写书评

暂无评论

Multi-graph aggregated graph neural network for heterogeneous graph representation learning

引用

INTERNATIONAL JOURNAL OF MACHINE learning AND CYBERNETICS 2025年第2期16卷 803-818页

作者： Zhu, Shuailei Wang, Xiaofeng Lai, Shuaiming Chen, Yuntao Zhai, Wenchao Quan, Daying Qi, Yuanyuan Lv, Laishui China Jiliang Univ Sch Informat Engn Hangzhou 310018 Zhejiang Peoples R China

Heterogeneous graph neural networks have attracted considerable attention for their proficiency in handling intricate heterogeneous structures. However, most existing methods model semantic relationships in heterogeneous graphs by manually defining meta-paths, inadvertently overlooking the inherent incompleteness of such graphs. To address this issue, we propose a multi-graph aggregated graph neural network (MGAGNN) for heterogeneous graph representation learning, which simultaneously leverages attribute similarity and high-order semantic information between nodes. Specifically, MGAGNN first employs the feature graph generator to generate a feature graph for completing the original graph structure. A semantic graph is then generated using a semantic graph generator, capturing higher-order semantic information through automatic meta-path learning. Finally, we aggregate the two candidate graphs to reconstruct a new heterogeneous graph and learn node embedding by graph convolutional networks. Extensive experiments on real-world datasets demonstrate the superior performance of the proposed method over state-of-the-art approaches.

关键词： graph neural network Heterogeneous graph Multi-graph aggregation graph representation learning

来源：评论

学校读者我要写书评

暂无评论

Commonsense knowledge enhanced event graph representation learning for script event prediction

引用

MACHINE learning 2025年第3期114卷 1-19页

作者： Li, Xiang Jiang, Xinxi Zhou, Qifeng Xiamen Univ Sch Aerosp Engn Xiamen 361106 Fujian Peoples R China

Script event prediction plays an important role in many artificial intelligence applications. A key challenge in this task is accurately understanding the correlation between events and then inferring the subsequent events. Benefiting from exploring the rich connections among events, recently some event graph-based methods have achieved remarkable success. However, limited by the abstract representation of events, it is often difficult to derive the event relationships fully and precisely from the original event graphs. In this paper, we propose a novel framework, called Commonsense knowledge-enhanced event evolutionary graph (CEEG), to remedy this problem. CEEG constructs two core modules, event evolutionary graph and event commonsense graph, the former incorporates connections among the predicate events and object events to find the potential information among events, while the latter utilizes external commonsense knowledge to further enhance the understanding of event relationships. Pre-trained model RoBERTa and graph Neural Network are also integrated into the framework to obtain more accuracy event nodes depiction and rich event graph information. Comprehensive experimental results on the benchmark dataset show the effectiveness of the proposed framework.

关键词： Script event prediction Event graph Commonsense knowledge graph representation learning

来源：评论

学校读者我要写书评

暂无评论

Attention-augmented multi-domain cooperative graph representation learning for molecular interaction prediction

引用

NEURAL NETWORKS 2025年 186卷 107265页

作者： Wang, Zhaowei Meng, Jun Li, Haibin Dai, Qiguo Li, Xiaohui Luan, Yushi Dalian Univ Technol Sch Comp Sci & Technol Dalian 116024 Peoples R China Dalian Minzu Univ Sch Comp Sci & Engn Dalian 116600 Peoples R China Dalian Univ Technol Sch Bioengn Dalian 116024 Peoples R China

Accurate identification of molecular interactions is crucial for biological network analysis, which can provide valuable insights into fundamental regulatory mechanisms. Despite considerable progress driven by computational advancements, existing methods often rely on task-specific prior knowledge or inherent structural properties of molecules, which limits their generalizability and applicability. Recently, graph-based methods have emerged as a promising approach for predicting links in molecular networks. However, most of these methods focus primarily on aggregating topological information within individual domains, leading to an inadequate characterization of molecular interactions. To mitigate these challenges, we propose AMCGRL, a generalized multi-domain cooperative graph representation learning framework for multifarious molecular interaction prediction tasks. Concretely, AMCGRL incorporates multiple graph encoders to simultaneously learn molecular representations from both intra-domain and inter-domain graphs in a comprehensive manner. Then, the cross-domain decoder is employed to bridge these graph encoders to facilitate the extraction of task- relevant information across different domains. Furthermore, a hierarchical mutual attention mechanism is developed to capture complex pairwise interaction patterns between distinct types of molecules through inter- molecule communicative learning. Extensive experiments conducted on the various datasets demonstrate the superior representation learning capability of AMCGRL compared to the state-of-the-art methods, proving its effectiveness in advancing the prediction of molecular interactions.

关键词： graph representation learning Molecular interaction graph transformer Cross-domain mutual learning Communicative learning

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation for graph representation learning: Challenges, Progress, and Prospects

引用

JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 2025年第2期40卷 283-300页

作者： Shi, Bo-Shen Wang, Yong-Qing Guo, Fang-Da Xu, Bing-Bing Shen, Hua-Wei Cheng, Xue-Qi Chinese Acad Sci Inst Comp Technol Key Lab AI Safety Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100190 Peoples R China

graph representation learning often faces knowledge scarcity in real-world applications, including limited labels and sparse relationships. Although a range of methods have been proposed to address these problems, such as graph few-shot learning, they mainly rely on inadequate knowledge within the task graph, which would limit their effectiveness. Moreover, they fail to consider other potentially useful task-related graphs. To overcome these limitations, domain adaptation for graph representation learning has emerged as an effective paradigm for transferring knowledge across graphs. It is also recognized as graph domain adaptation (GDA). In particular, to enhance model performance on target graphs with specific tasks, GDA introduces a bunch of task-related graphs as source graphs and adapts the knowledge learnt from source graphs to the target graphs. Since GDA combines the advantages of graph representation learning and domain adaptation, it has become a promising direction of transfer learning on graphs and has attracted an increasing amount of research interest in recent years. In this paper, we comprehensively overview the studies of GDA and present a detailed survey of recent advances. Specifically, we outline the current research status, analyze key challenges, propose a taxonomy, introduce representative work and practical applications, and discuss future prospects. To the best of our knowledge, this paper is the first survey for graph domain adaptation.

关键词： graph domain adaptation graph representation learning transfer 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：