Scholarlink

<p>Link prediction seeks to uncover potential or future connections within a network using structural or attribute information. Recently, Graph Neural Network (GNN)-based methods have attracted considerable attention for their effectiveness in link prediction. However, most GNN-based approaches focus solely on single-scale input graphs, which limits their ability to comprehensively capture network structure information. In this paper, multi-scale subgraphs are introduced as input graphs to obtain complementary network structures from different perspectives. Simultaneously, to obtain embedding vectors with better representational capacity, contrastive loss from self-supervised learning is incorporated for link prediction. Specifically, <Emphasis Type="BoldUnderline">M</Emphasis>ulti-scale <Emphasis Type="BoldUnderline">C</Emphasis>ontrastive learning framework based on <Emphasis Type="BoldUnderline">A</Emphasis>ggregated <Emphasis Type="BoldUnderline">S</Emphasis>ubgraph (MCAS) is proposed for predicting missing links. Firstly, we construct enclosing subgraph by extracting neighbors of target nodes. By applying aggregation operation to these subgraphs, different granularities of multi-scale subgraphs are obtained. Secondly, encoders are used to learn information from multiple scales of subgraphs separately. Next, contrastive learning is employed to achieve information balance among the multi-scale subgraphs. Finally, the minimization of the loss allows us to improve the model’s robustness. Empirical evidence indicates that our approach excels state-of-the-art methods on nine datasets, including biological and citation networks. All source code is publicly available at: <a href="https://github.com/yabingyao/MCAS4LinkPrediction">https://github.com/yabingyao/MCAS4LinkPrediction</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Multi-scale contrastive learning via aggregated subgraph for link prediction

  • 期刊论文

  • 发表日期：

    2025年2月28日

查看全文
  • Yabing Yao,
  • Pingxia Guo,
  • Zhiheng Mao,
  • Ziyu Ti,
  • Yangyang He,
  • Fuzhong Nian,
  • Ruisheng Zhang,
  • Ning Ma

摘要

Link prediction seeks to uncover potential or future connections within a network using structural or attribute information. Recently, Graph Neural Network (GNN)-based methods have attracted considerable attention for their effectiveness in link prediction. However, most GNN-based approaches focus solely on single-scale input graphs, which limits their ability to comprehensively capture network structure information. In this paper, multi-scale subgraphs are introduced as input graphs to obtain complementary network structures from different perspectives. Simultaneously, to obtain embedding vectors with better representational capacity, contrastive loss from self-supervised learning is incorporated for link prediction. Specifically, Multi-scale Contrastive learning framework based on Aggregated Subgraph (MCAS) is proposed for predicting missing links. Firstly, we construct enclosing subgraph by extracting neighbors of target nodes. By applying aggregation operation to these subgraphs, different granularities of multi-scale subgraphs are obtained. Secondly, encoders are used to learn information from multiple scales of subgraphs separately. Next, contrastive learning is employed to achieve information balance among the multi-scale subgraphs. Finally, the minimization of the loss allows us to improve the model’s robustness. Empirical evidence indicates that our approach excels state-of-the-art methods on nine datasets, including biological and citation networks. All source code is publicly available at: https://github.com/yabingyao/MCAS4LinkPrediction.