Article
Computer Science, Artificial Intelligence
Cheng-Te Li, Wei-Chu Wang
Summary: Network representation learning (NRL) is effective in generating node embeddings. However, existing studies on heterogeneous link prediction suffer from drawbacks such as the need for templates, separate embedding learning, and low-quality embeddings in incomplete networks. This work proposes a template-free method, metawalk2vec, which allows random walkers to visit diverse nodes, leading to improved node embeddings. Experiments on social and adoption link predictions show that metawalk2vec outperforms template-based models and is more robust to network incompleteness.
Article
Mathematics
Jiaping Cao, Jichao Li, Jiang Jiang
Summary: Link prediction for temporal heterogeneous networks is addressed in this paper, where a novel link prediction method (LP-THN) based on the information lifecycle is proposed. LP-THN takes into account the evolution of network structure and semantic changes by using meta-path augmented residual information matrix perturbations. Experimental results demonstrate the superiority of LP-THN over other baselines in terms of prediction effectiveness and efficiency.
Article
Computer Science, Artificial Intelligence
Zehua Zhang, Shilin Sun, Guixiang Ma, Caiming Zhong
Summary: Link prediction tasks focus on predicting possible future connections. Most existing researches measure the likelihood of links by different similarity scores on node pairs and predict links between nodes. However, similarity-based approaches have challenges in information loss on nodes and generalization ability on similarity indexes. To address these issues, we propose a Line Graph Contrastive Learning (LGCL) method that obtains rich information with multiple perspectives. LGCL uses h-hop subgraph sampling and transforms the subgraph into a line graph to convert the link prediction task into a node classification task. Additionally, a novel cross-scale contrastive learning framework is designed to fuse structure and feature information. Experimental results show that the proposed LGCL outperforms state-of-the-art methods in generalization and robustness.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Haoyi Fan, Fengbin Zhang, Yuxuan Wei, Zuoyong Li, Changqing Zou, Yue Gao, Qionghai Dai
Summary: This paper presents a method named HeteHG-VAE for link prediction in heterogeneous information networks. It maps a conventional HIN to a heterogeneous hypergraph with specific semantics to capture high-order semantics and complex relations among nodes, and learns deep latent representations of nodes and hyperedges from the heterogeneous hypergraph using a Bayesian deep generative framework. Experimental results demonstrate the effectiveness and efficiency of the proposed method.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Xi Wang, Yibo Chai, Hui Li, Danqin Wu
Summary: A study has developed an improved spatial graph convolution network for link prediction in heterogeneous information networks, achieving better results compared to benchmark algorithms and providing insights for the design of information systems.
DECISION SUPPORT SYSTEMS
(2021)
Article
Physics, Multidisciplinary
Jiating Yu, Ling-Yun Wu
Summary: Link prediction is a classical problem in the field of complex networks, which is of great significance for understanding the evolution and dynamic development mechanisms of networks. This study proposes a novel method called MOLI, which utilizes local information from neighbors at different distances and defines a local network diffusion process via random walks on the graph, achieving better utilization of network information. The results show that MOLI outperforms other widely used link prediction methods on different types of networks.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Hao Shao, Lunwen Wang, Rangang Zhu
Summary: Heterogeneous link prediction aims to reveal potential connections between nodes in heterogeneous networks. Existing studies based on meta-paths ignore the information in incomplete meta-paths, leading to insufficient mining of semantic information. To solve this problem, we propose a model that compensates for the deficiency of incomplete meta-paths by aggregating structural features and semantics. We use recurrent neural networks and attention mechanism to learn explicit and implicit semantic knowledge and design a bidirectional biased random walking algorithm to acquire complete topological information. The proposed model outperforms baselines in extensive experiments on multiple datasets.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2023)
Article
Mechanics
Ting Zhang, Kun Zhang, Laishui Lv, Xun Li, Yue Fang
Summary: This paper introduces a novel link prediction method based on non-negative tensor factorization that improves the performance of link prediction in temporal directed networks by effectively considering link direction and temporal information.
JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT
(2021)
Article
Computer Science, Artificial Intelligence
Yuncong Zhao, Yiyang Sun, Yaning Huang, Longjie Li, Hu Dong
Summary: In this paper, an end-to-end link prediction method for heterogeneous networks is proposed. It leverages metapath projection and semantic graph aggregation to learn the embeddings of node pairs from different metapaths. The empirical study shows that the proposed method outperforms competing methods in terms of prediction accuracy.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Management
Zhen-Yu Chen, Zhi-Ping Fan, Minghe Sun
Summary: Tensorial graph learning frameworks are proposed for link predictions in heterogeneous, homogeneous and generalized heterogeneous networks. A tensorial graph kernel method is developed to measure node similarities and integrate results in different networks, showing better performance than existing competitive methods.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2021)
Article
Computer Science, Artificial Intelligence
Yifan Lu, Mengzhou Gao, Huan Liu, Zehao Liu, Wei Yu, Xiaoming Li, Pengfei Jiao
Summary: NOH is a neural network model that utilizes structural information and estimates overlapped neighborhood from a heterogeneous graph for link prediction. It addresses the limitations of existing models that only consider low-order pairwise relations and node attributes, neglecting higher-order group interactions. Experimental results on four real-world datasets demonstrate that NOH consistently achieves state-of-the-art performance on link prediction.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Information Systems
Kamal Berahmand, Elahe Nasiri, Saman Forouzandeh, Yuefeng Li
Summary: This article proposes an improved method for local random walk by encouraging the movement towards nodes with stronger influence, resulting in higher prediction accuracy. A comparison with other similarity-based methods was conducted on 11 real-world networks, and the results demonstrated its superior performance in link prediction.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
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
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, Information Systems
Jianxing Zheng, Zifeng Qin, Suge Wang, Deyu Li
Summary: This paper presents an explainable method for friend link recommendation in recommender systems. It leverages the similarity of user pairs using fusion embedding and incorporates external knowledge semantics. The proposed method considers both direct and indirect factors in predicting friend links and provides a good interpretation of the recommendation results.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Interdisciplinary Applications
Hadi Shakibian, Nasrollah Moghadam Charkari, Saeed Jalili
JOURNAL OF COMPUTATIONAL SCIENCE
(2016)
Article
Computer Science, Artificial Intelligence
Hadi Shakibian, Nasrollah Moghadam Charkari, Saeed Jalili
APPLIED INTELLIGENCE
(2018)
Article
Physics, Multidisciplinary
Hadi Shakibian, Nasrollah Moghadam Charkari
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2018)
Article
Computer Science, Hardware & Architecture
Hadi Shakibian, Nasrollah Moghadam Charkari
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2014)
Review
Endocrinology & Metabolism
Mozhgan Tanhapour, Maryam Peimani, Sharareh Rostam Niakan Kalhori, Ensieh Nasli Esfahani, Hadi Shakibian, Niloofar Mohammadzadeh, Mostafa Qorbani
Summary: Type 2 diabetes is increasing globally, and self-care plays an important role in preventing complications. Lack of knowledge is a barrier to successful self-care. Intelligent digital health solutions have the potential to train patients in self-care behaviors based on their individual needs. This study reviews the effects of randomized controlled trials offering individualized self-care training systems for patients with type 2 diabetes.
ACTA DIABETOLOGICA
(2023)
Proceedings Paper
Engineering, Electrical & Electronic
Nasrin Torabi, Hadi Shakibian, Nasrollah Moghadam charkari
2016 24TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE)
(2016)
Proceedings Paper
Engineering, Electrical & Electronic
Hadi Shakibian, Nasrollah Moghadam Charkari
2016 24TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE)
(2016)