Node Classification with Multi-hop Graph Convolutional Network

被引:0
|
作者
Jui, Tonni Das [1 ]
Benton, Mary Lauren [1 ]
Baker, Erich [2 ]
机构
[1] Baylor Univ, Waco, TX 76706 USA
[2] Belmont Univ, Nashville, TN 37212 USA
来源
RECENT ADVANCES IN NEXT-GENERATION DATA SCIENCE, SDSC 2024 | 2024年 / 2158卷
关键词
Graph embedding; Graph structure; Global information; Multi-hop; Node classification;
D O I
10.1007/978-3-031-67871-4_14
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Various graph neural network architectures have emerged, each focusing on different facets of graphs, such as ensuring scalability, preserving local structures, and retaining structural and feature information within the node vectors. However, incorporating global structures into the latent representation is frequently overlooked despite being a central focus of many random-walk-based embedding techniques predating the advent of graph neural networks. Ensuring the preservation of global structural information enriches the node representations to tackle the node classification task effectively. We introduce an innovative multi-hopped graph convolutional network designed for graph-structured data to address this gap. This architecture leverages adjacent node information and incorporates distanced neighborhood information to preserve global structure in the latent representations. We propose a method for aggregating multiple hopped features and devise a straightforward yet effective architecture. Empirical validation of our theoretical findings on various graph classification benchmarks showcases that our model attains state-of-the-art and consistent performance.
引用
收藏
页码:199 / 213
页数:15
相关论文
共 50 条
  • [1] Multi-hop Question Generation with Graph Convolutional Network
    Su, Dan
    Xu, Yan
    Dai, Wenliang
    Ji, Ziwei
    Yu, Tiezheng
    Fung, Pascale
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020, : 4636 - 4647
  • [2] Robust graph contrastive learning with multi-hop views for node classification
    Wang, Yutong
    Zhang, Junheng
    Cao, Ren
    Zou, Minhao
    Guan, Chun
    Leng, Siyang
    APPLIED SOFT COMPUTING, 2025, 171
  • [3] ConvHiA: convolutional network with hierarchical attention for knowledge graph multi-hop reasoning
    Dengao Li
    Shuyi Miao
    Baofeng Zhao
    Yu Zhou
    Ding Feng
    Jumin Zhao
    Xupeng Niu
    International Journal of Machine Learning and Cybernetics, 2023, 14 : 2301 - 2315
  • [4] ConvHiA: convolutional network with hierarchical attention for knowledge graph multi-hop reasoning
    Li, Dengao
    Miao, Shuyi
    Zhao, Baofeng
    Zhou, Yu
    Feng, Ding
    Zhao, Jumin
    Niu, Xupeng
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2023, 14 (07) : 2301 - 2315
  • [5] Multi-hop assortativities for network classification
    Gutierrez-Gomez, Leonardo
    Delvenne, Jean-Charles
    JOURNAL OF COMPLEX NETWORKS, 2019, 7 (04) : 603 - 622
  • [6] Multi-hop Syntactic Graph Convolutional Networks for Aspect-Based Sentiment Classification
    Yin, Chang
    Zhou, Qing
    Ge, Liang
    Ou, Jiaojiao
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT (KSEM 2020), PT II, 2020, 12275 : 213 - 224
  • [7] Hierarchical Graph Network for Multi-hop Question Answering
    Fang, Yuwei
    Sun, Siqi
    Gan, Zhe
    Pillai, Rohit
    Wang, Shuohang
    Liu, Jingjing
    PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 8823 - 8838
  • [8] Dynamically Fused Graph Network for Multi-hop Reasoning
    Qiu, Lin
    Xiao, Yunxuan
    Qu, Yanru
    Zhou, Hao
    Li, Lei
    Zhang, Weinan
    Yu, Yong
    57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 6140 - 6150
  • [9] Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network
    Tang, Zeyun
    Shen, Yongliang
    Ma, Xinyin
    Xu, Wei
    Yu, Jiale
    Lu, Weiming
    PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 3905 - 3911
  • [10] Cnn-assisted multi-hop graph attention network for hyperspectral image classification
    Wang, Hongxi
    Guo, Wenhui
    Wang, Xueqin
    Wang, Yanjiang
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2024, 45 (22) : 8258 - 8289