Graph Communal Contrastive Learning

被引:24
|
作者
Li, Bolian [1 ]
Jing, Baoyu [2 ]
Tong, Hanghang [2 ]
机构
[1] Tianjin Univ, Tianjin, Peoples R China
[2] Univ Illinois, Champaign, IL USA
基金
美国国家科学基金会;
关键词
self-supervised learning; graph contrastive learning; community detection; NETWORK;
D O I
10.1145/3485447.3512208
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Graph representation learning is crucial for many real-world applications (e.g. social relation analysis). A fundamental problem for graph representation learning is how to effectively learn representations without human labeling, which is usually costly and time-consuming. Graph contrastive learning (GCL) addresses this problem by pulling the positive node pairs (or similar nodes) closer while pushing the negative node pairs (or dissimilar nodes) apart in the representation space. Despite the success of the existing GCL methods, they primarily sample node pairs based on the node-level proximity yet the community structures have rarely been taken into consideration. As a result, two nodes from the same community might be sampled as a negative pair. We argue that the community information should be considered to identify node pairs in the same communities, where the nodes insides are semantically similar. To address this issue, we propose a novel Graph Communal Contrastive Learning (gCooL) framework to jointly learn the community partition and learn node representations in an end-to-end fashion. Specifically, the proposed gCooL consists of two components: a Dense Community Aggregation (DeCA) algorithm for community detection and a Reweighted Self-supervised Cross-contrastive (ReSC) training scheme to utilize the community information. Additionally, the real-world graphs are complex and often consist of multiple views. In this paper, we demonstrate that the proposed gCooL can also be naturally adapted to multiplex graphs. Finally, we comprehensively evaluate the proposed gCooL on a variety of real-world graphs. The experimental results show that the gCooL outperforms the state-of-the-art methods.
引用
收藏
页码:1203 / 1213
页数:11
相关论文
共 50 条
  • [1] Asymmetric Graph Contrastive Learning
    Chang, Xinglong
    Wang, Jianrong
    Guo, Rui
    Wang, Yingkui
    Li, Weihao
    [J]. MATHEMATICS, 2023, 11 (21)
  • [2] Hierarchical Graph Contrastive Learning
    Yan, Hao
    Wang, Senzhang
    Yin, Jun
    Li, Chaozhuo
    Zhu, Junxing
    Wang, Jianxin
    [J]. MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: RESEARCH TRACK, ECML PKDD 2023, PT II, 2023, 14170 : 700 - 715
  • [3] Prototypical Graph Contrastive Learning
    Lin, Shuai
    Liu, Chen
    Zhou, Pan
    Hu, Zi-Yuan
    Wang, Shuojia
    Zhao, Ruihui
    Zheng, Yefeng
    Lin, Liang
    Xing, Eric
    Liang, Xiaodan
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (02) : 2747 - 2758
  • [4] Graph Contrastive Learning Automated
    You, Yuning
    Chen, Tianlong
    Shen, Yang
    Wang, Zhangyang
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [5] Directed Graph Contrastive Learning
    Tong, Zekun
    Liang, Yuxuan
    Ding, Henghui
    Dai, Yongxing
    Li, Xinke
    Wang, Changhu
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [6] Graph prototypical contrastive learning
    Peng, Meixin
    Juan, Xin
    Li, Zhanshan
    [J]. INFORMATION SCIENCES, 2022, 612 : 816 - 834
  • [7] Graph Contrastive Learning with Augmentations
    You, Yuning
    Chen, Tianlong
    Sui, Yongduo
    Chen, Ting
    Wang, Zhangyang
    Shen, Yang
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [8] Contrastive Graph Learning with Graph Convolutional Networks
    Nagendar, G.
    Sitaram, Ramachandrula
    [J]. DOCUMENT ANALYSIS SYSTEMS, DAS 2022, 2022, 13237 : 96 - 110
  • [9] AGCL: Adaptive Graph Contrastive Learning for graph representation learning
    Yu, Jiajun
    Jia, Adele Lu
    [J]. NEUROCOMPUTING, 2024, 566
  • [10] Graph Contrastive Learning with Constrained Graph Data Augmentation
    Xu, Shaowu
    Wang, Luo
    Jia, Xibin
    [J]. NEURAL PROCESSING LETTERS, 2023, 55 (08) : 10705 - 10726