Graph Sparsification with Generative Adversarial Network

被引:2
|
作者
Wu, Hang-Yang [1 ]
Chen, Yi-Ling [1 ]
机构
[1] Natl Taiwan Univ Sci & Technol, Dept Comp Sci & Informat Engn, Taipei, Taiwan
关键词
Graph sparsification; Deep learning; Social network analysis;
D O I
10.1109/ICDM50108.2020.00172
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Graph sparsification aims to reduce the number of edges of a network while maintaining its accuracy for given tasks. In this study, we propose a novel method called GSGAN, which is able to sparsify networks for community detection tasks. GSGAN is able to capture those relationships that are not shown in the original graph but are relatively important, and creating artificial edges to reflect these relationships and further increase the effectiveness of the community detection task. We adopt GAN as the learning model and guide the generator to produce random walks that are able to capture the structure of a network. Specifically, during the training phase, in addition to judging the authenticity of the random walk, discriminator also considers the relationship between nodes at the same time. We design a reward function to guide the generator creating random walks that contain useful hidden relation information. These random walks are then combined to form a new social network that is efficient and effective for community detection. Experiments with real-world networks demonstrate that the proposed GSGAN is much more effective than the baselines, and GSGAN can be applied and helpful to various clustering algorithms of community detection.
引用
收藏
页码:1328 / 1333
页数:6
相关论文
共 50 条
  • [1] Graph Contrastive Learning with Generative Adversarial Network
    Wu, Cheng
    Wang, Chaokun
    Xu, Jingcao
    Liu, Ziyang
    Zheng, Kai
    Wang, Xiaowei
    Song, Yang
    Gai, Kun
    [J]. PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, 2023, : 2721 - 2730
  • [2] Generative Adversarial Network Rooms in Generative Graph Grammar Dungeons for The Legend of Zelda
    Gutierrez, Jake
    Schrum, Jacob
    [J]. 2020 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2020,
  • [3] Image and Graph Restoration Dependent on Generative Adversarial Network Algorithm
    Cao, Yuanhao
    [J]. TEHNICKI VJESNIK-TECHNICAL GAZETTE, 2021, 28 (06): : 1820 - 1824
  • [4] RegraphGAN: A graph generative adversarial network model for dynamic network anomaly detection
    Guo, Dezhi
    Liu, Zhaowei
    Li, Ranran
    [J]. NEURAL NETWORKS, 2023, 166 : 273 - 285
  • [5] Recommendation System Based on Generative Adversarial Network with Graph Convolutional Layers
    Sasagawa, Takato
    Kawai, Shin
    Nobuhara, Hajime
    [J]. JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS, 2021, 25 (04) : 389 - 396
  • [6] ImGAGN: Imbalanced Network Embedding via Generative Adversarial Graph Networks
    Qu, Liang
    Zhu, Huaisheng
    Zheng, Ruiqi
    Shi, Yuhui
    Yin, Hongzhi
    [J]. KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2021, : 1390 - 1398
  • [7] Negative Sampling for Knowledge Graph Completion Based on Generative Adversarial Network
    Le, Thanh
    Pham, Trinh
    Le, Bac
    [J]. COMPUTATIONAL COLLECTIVE INTELLIGENCE (ICCCI 2021), 2021, 12876 : 3 - 15
  • [8] Road Network Data Repair Based on Graph Autoencoder-generative Adversarial Network
    Xu, Dong-Wei
    Peng, Hang
    Shang, Xue-Tian
    Wei, Chen-Chen
    Yang, Yan-Fang
    [J]. Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology, 2021, 21 (06): : 33 - 41
  • [9] Generative Adversarial Network-assisted Graph Convolutional Network (GANA-GCN)
    Li, Kangjie
    [J]. Proceedings of the International Joint Conference on Neural Networks, 2022, 2022-July
  • [10] Generative Adversarial Network-assisted Graph Convolutional Network (GANA-GCN)
    Li, Kangjie
    [J]. 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,