Scholarlink

<p>Network alignment seeks to identify corresponding nodes across graphs, a task that is challenging when structural signals are weak or noisy. Existing optimization-based methods offer strong accuracy but do not scale well, while embedding-based methods are efficient yet often less precise. We propose <i>SST-Align</i>, a hybrid alignment framework that combines the strengths of both paradigms: a topology-driven initialization followed by self-supervised representation learning. Across six real-world datasets, <i>SST-Align</i> achieves competitive or superior node-mapping accuracy compared to strong graph alignment baselines. Under increasing structural noise, <i>SST-Align</i> remains robust and typically matches the performance of non-pretrained methods. We further demonstrate that <i>SST-Align</i> generalizes to heterogeneous networks through a simple extension incorporating node-type awareness.</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

Graphlet-based self-supervised model for topological network alignment

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月27日

查看全文
  • Abdullah Al Fahad,
  • Aljohara Almulhim,
  • Mohammad Al Hasan

摘要

Network alignment seeks to identify corresponding nodes across graphs, a task that is challenging when structural signals are weak or noisy. Existing optimization-based methods offer strong accuracy but do not scale well, while embedding-based methods are efficient yet often less precise. We propose SST-Align, a hybrid alignment framework that combines the strengths of both paradigms: a topology-driven initialization followed by self-supervised representation learning. Across six real-world datasets, SST-Align achieves competitive or superior node-mapping accuracy compared to strong graph alignment baselines. Under increasing structural noise, SST-Align remains robust and typically matches the performance of non-pretrained methods. We further demonstrate that SST-Align generalizes to heterogeneous networks through a simple extension incorporating node-type awareness.