Article
Computer Science, Artificial Intelligence
Xiaoyang Liu, Xiang Li, Giacomo Fiumara, Pasquale De Meo
Summary: This paper proposes a link prediction approach that combines Graph Neural Networks (GNNs) with Capsule Networks (CapsNet). The method transforms node embeddings into a node pair feature map and uses CapsNets to learn the feature representation, achieving better accuracy than competitor methods.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Mathematics, Interdisciplinary Applications
Jiayun Wu, Langzhou He, Tao Jia, Li Tao
Summary: In this paper, a high-accuracy white-box TLP algorithm called DMAB is proposed by shifting the perspective of link prediction to the microscopic level of nodes. Two dynamic properties, node activity and node loyalty, are extracted and quantified to build the DMAB model. Comparative experiments with six state-of-the-art black-box methods on 12 real networks demonstrate that DMAB achieves excellent prediction performance and effectively captures network evolution mechanisms.
CHAOS SOLITONS & FRACTALS
(2023)
Article
Computer Science, Information Systems
Zongqian Wu, Mengmeng Zhan, Haiqi Zhang, Qimin Luo, Kun Tang
Summary: In this paper, a Multi-Task and Multi-Graph Convolutional Network (MTGCN) is proposed to conduct node classification and link prediction simultaneously. MTGCN consists of multiple multi-task learning to capture the complementary information between node classification and link prediction, and enhances the information to guarantee the quality of representations by exploring the complex structure inherent in the graph data.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Computer Science, Information Systems
Huanran Wang, Wu Yang, Dapeng Man, Wei Wang, Jiguang Lv, Meng Joo Er
Summary: This paper proposes a novel method for anchor link prediction across different social networks. The method utilizes graph embedding and cross-network feature mining to construct an effective feature space, overcoming the limitations of traditional methods in real-life applications.
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Yunpeng Xiao, Rui Li, Xingyu Lu, Yanbing Liu
Summary: This paper proposes a link prediction method based on feature representation and fusion, which involves steps like network embedding and text vector conversion, and eventually introduces a convolutional neural network with attention mechanism. Experimental results demonstrate that the model effectively improves the performance of link prediction.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Rui Tang, Shuyu Jiang, Xingshu Chen, Wenxian Wang, Wei Wang
Summary: Interlayer link prediction aims to match the same entities across different layers of the multiplex network. Existing studies focus on predicting from aspects of network structure, attribute characteristics, etc., with few analyzing the effects of intralayer links. This research proposes two network structural perturbation methods and finds that the intralayer links connected with small degree nodes have the most significant impact on the prediction accuracy.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Rahul Saxena, Spandan Pankaj Patil, Atul Kumar Verma, Mahipal Jadeja, Pranshu Vyas, Vikrant Bhateja, Jerry Chun-Wei Lin
Summary: Link prediction is the task of determining whether a link will exist between two entities. In this study, we propose a network centrality-based approach combined with Graph Convolution Networks (GCNs) to predict connections between network nodes. Our model achieves high prediction accuracies of 95.08%, 95.07%, and 95.3% on benchmark datasets, demonstrating its effectiveness.
INTERNATIONAL JOURNAL OF INTERACTIVE MULTIMEDIA AND ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Anping Zhao, Yu Yu
Summary: The proposed method effectively predicts sentiment links among users by combining global structural information with multi-dimensional relations and heterogeneous context information. Experimental results demonstrate the effectiveness of incorporating social relations and profile context information into sentiment link prediction, especially in cold-start scenarios.
COGNITIVE COMPUTATION
(2022)
Article
Physics, Multidisciplinary
Yan-Li Lee, Tao Zhou
Summary: The study introduces an enhancement framework for local indices based on collaborative filtering, and further proposes a self-included collaborative filtering framework, significantly improving the accuracy and robustness of well-known local indices.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Yujie Yang, Long Wang, Dong Liu
Summary: This paper proposes an anchor link prediction method based on multiple consistency (MC), which utilizes interlayer and intralayer structures for improved performance in several real networks.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Information Systems
Feipeng Guo, Wei Zhou, Qibei Lu, Chen Zhang
Summary: This paper proposes a directed network link prediction method based on path extension similarity, which improves the prediction accuracy by utilizing the network paths between nodes. Experimental results demonstrate that this method achieves higher accuracy and robustness compared to traditional methods.
COMPUTER COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Ming-Ren Chen, Ping Huang, Yu Lin, Shi-Min Cai
Summary: This study introduces a novel graph embedding model SSNE for link prediction in sparse networks, which transforms the adjacency matrix and maps it to obtain node representation for nodal similarity calculation and link prediction. Experimental results demonstrate that SSNE outperforms other models in sparse networks.
Article
Computer Science, Artificial Intelligence
Yadan Luo, Zi Huang, Hongxu Chen, Yang Yang, Hongzhi Yin, Mahsa Baktashmotlagh
Summary: Signed link prediction in social networks aims to reveal the underlying relationships (i.e., links) among users (i.e., nodes) given their existing interactions. Existing graph-based approaches lack human-intelligible explanations for key questions, and thus a new framework, SIHG, is proposed. SIHG incorporates a signed attention module to identify representative neighboring nodes and preserve the geometry of antagonism. Extensive experiments demonstrate that SIHG outperforms existing methods in signed link prediction.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Oguz Findik, Emrah Ozkaynak
Summary: Link prediction is crucial for forecasting future links in complex networks, with traditional methods often falling short due to limited consideration of node weighting. This study proposes a novel model based on node weighting, showing superior success rates compared to current technology methods.
Article
Mathematics
Chunning Wang, Fengqin Tang, Xuejing Zhao
Summary: The individuals of real-world networks form layers in multiplex networks with various types of connections. Link prediction is a crucial problem in multiplex network analysis and has practical applications in mining drug targets, recommending friends in social networks, and exploring network evolution mechanisms. Incorporating interlayer topological information can improve the performance of link prediction in the predicted layer. Therefore, this paper proposes the Link Prediction based on Global Relevance of Interlayer (LPGRI) method that comprehensively utilizes both interlayer and intralayer information to estimate the likelihood of potential links in multiplex networks.
Article
Computer Science, Interdisciplinary Applications
Lu An, Xia Lin, Chuanming Yu, Xinwen Zhang
Editorial Material
Computer Science, Software Engineering
Xia Lin, Andreas Kerren, Jiaje Zhang
INFORMATION VISUALIZATION
(2009)
Article
Computer Science, Information Systems
Lu An, Chuanming Yu, Xia Lin, Tingyao Du, Liqin Zhou, Gang Li
ONLINE INFORMATION REVIEW
(2018)
Article
Information Science & Library Science
Xia Lin, Michael Khoo, Jae-Wook Ahn, Doug Tudhope, Ceri Binding, Diana Massam, Hilary Jones
INTERNATIONAL JOURNAL ON DIGITAL LIBRARIES
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Lu An, Liqin Zhou, Xia Lin, Chuanming Yu
DIGITAL LIBRARIES: PROVIDING QUALITY INFORMATION
(2015)
Article
Computer Science, Information Systems
Michael John Khoo, Jae-Wook Ahn, Ceri Binding, Hilary Jane Jones, Xia Lin, Diana Massam, Douglas Tudhope
JOURNAL OF DOCUMENTATION
(2015)
Article
Cell Biology
Sokol Petushi, Jeffrey Marker, Jasper Zhang, Weizhong Zhu, David Breen, Chaomei Chen, Xia Lin, Fernando U. Garcia
ANALYTICAL AND QUANTITATIVE CYTOLOGY AND HISTOLOGY
(2008)
Article
Multidisciplinary Sciences
HD White, X Lin, JW Buzydlowski, CM Chen
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2004)
Article
Computer Science, Information Systems
X Lin, HD White, J Buzydlowski
INFORMATION PROCESSING & MANAGEMENT
(2003)