Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Shivansh Mishra et al.
Summary: This paper investigates the encoding and layering structure of different types of connections in multiplex networks. By combining the structure of all layers, a complete overview of the network is achieved, allowing for determination of regional influence of nodes and accurate link prediction. An aggregation model is used to combine information from multiple layers, and an algorithm is proposed to calculate link likelihoods by considering longer paths between nodes. The results show that this technique outperforms state-of-the-art multiplex link prediction algorithms.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Weijian Chen et al.
Summary: Recent studies have shown that the initial node representations in Graph Convolutional Networks (GCNs) significantly affect the final model performance. However, existing methods typically combine node embeddings linearly without considering feature interactions, which are important for categorical node features. In this paper, we propose CatGCN, a new GCN model specially designed for learning on categorical node features. We introduce two types of explicit interaction modeling to enhance the initial node representations before applying graph convolution. Experimental results on user profiling tasks demonstrate the effectiveness of CatGCN, particularly the positive impact of feature interaction modeling before graph convolution.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Amina Amara et al.
Summary: In this paper, a novel deep learning model is proposed to learn low-dimensional vector representations for anchor users in multiple social networks. By considering both the intra-network and cross-network structural information, the proposed model shows improved performance in link prediction tasks compared to existing network representation learning approaches.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Interdisciplinary Applications
Shivansh Mishra et al.
Summary: In this work, the focus is on link prediction in multiplex networks, where nodes can have multiple relationships encoded in different layers. The study proposes a methodology that considers both edge and node relevance to accurately predict links between unconnected nodes. An aggregation model is used to summarize the information from different layers into a weighted static network, and an algorithm is developed to calculate node and edge relevance based on this graph. The results show that the proposed method outperforms classical link prediction methods for weighted graphs.
JOURNAL OF COMPUTATIONAL SCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Xinyi Zhang et al.
Summary: This paper introduces a novel meta-path based HIN representation learning framework called mSHINE, which simultaneously learns multiple node representations for different meta-paths and measures the relevance between nodes using a designed objective function. Additionally, a set of criteria for selecting initial meta-paths is proposed to reduce the cost of meta-path selection. Experimental results demonstrate that mSHINE outperforms other methods in node classification and link prediction tasks.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Tinglin Huang et al.
Summary: This study proposes a negative sampling method that leverages both the user-item graph structure and GNNs' aggregation process through the MixGCF technique to synthesize challenging negative samples in recommendation systems. Experimental results show that applying MixGCF can significantly improve the performance of GNN-based recommendation models.
KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Junliang Yu et al.
Summary: This paper proposes a multi-channel hypergraph convolutional network to enhance social recommendation by leveraging high-order user relations, obtaining comprehensive user representations for recommendation results. Additionally, by integrating self-supervised learning and hierarchical mutual information maximization, the model compensates for aggregating losses and regains connectivity information effectively.
PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE 2021 (WWW 2021)
(2021)
Review
Physics, Multidisciplinary
Ajay Kumar et al.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2020)
Review
Computer Science, Hardware & Architecture
Nur Nasuha Daud et al.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2020)
Proceedings Paper
Computer Science, Information Systems
Chuxu Zhang et al.
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING
(2019)
Proceedings Paper
Computer Science, Information Systems
Yukuo Cen et al.
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING
(2019)
Proceedings Paper
Computer Science, Theory & Methods
Xiao Wang et al.
WEB CONFERENCE 2019: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2019)
(2019)
Article
Biochemical Research Methods
Marinka Zitnik et al.
Proceedings Paper
Computer Science, Artificial Intelligence
Yuxiao Dong et al.
KDD'17: PROCEEDINGS OF THE 23RD ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING
(2017)
Proceedings Paper
Computer Science, Information Systems
Sumit Negi et al.
CIKM'16: PROCEEDINGS OF THE 2016 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT
(2016)
Proceedings Paper
Computer Science, Theory & Methods
Julian McAuley et al.
SIGIR 2015: PROCEEDINGS OF THE 38TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL
(2015)
Review
Physics, Multidisciplinary
Linyuan Lue et al.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2011)
