Scholarlink

<p>With the rapid development of artificial intelligence, knowledge graphs have become increasingly important for many downstream reasoning tasks. Although large-scale knowledge graphs have been constructed in many domains, many relations still suffer from data sparsity, making few-shot knowledge graph completion a practical and challenging problem. Existing methods typically enhance entity embeddings by aggregating one-hop neighbors. However, these neighbors often contain many irrelevant entities to the target relation, which introduces a large amount of noise. And existing methods are not sensitive to the semantic differences and task characteristics in the reference set, which leads to a lack of deep semantic meanings in relation representations and weakens relation inference. To address these challenges, we propose meta learning based few shot knowledge graph completion with domain selected aggregation. Specifically, the method introduces a domain-selected neighborhood aggregation mechanism that dynamically filters irrelevant neighbors through a selection strategy and a gating module, effectively suppressing noise propagation under sparse data conditions. Moreover, a relation meta-learner is designed by integrating contextual attention with a multi-layer perceptron to capture deep semantic correlations among reference triples and generate more expressive task-aware relational representations. An embedding learner further utilizes a meta-optimization strategy to enable rapid adaptation to new tasks. Experiments on NELL-One and Wiki-One datasets demonstrate that the method significantly outperforms state-of-the-art baselines. Specifically, in 5-shot tasks, it achieves performance improvements of <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(1.6\%\)</EquationSource> </InlineEquation> and <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(0.9\%\)</EquationSource> </InlineEquation> on the Hits@10 metric for datasets, respectively.</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

Meta learning based few shot knowledge graph completion with domain selected aggregation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月6日

查看全文
  • Bin Yang,
  • Mengxiang Peng,
  • Shuai Liu,
  • Mengqi Shi

摘要

With the rapid development of artificial intelligence, knowledge graphs have become increasingly important for many downstream reasoning tasks. Although large-scale knowledge graphs have been constructed in many domains, many relations still suffer from data sparsity, making few-shot knowledge graph completion a practical and challenging problem. Existing methods typically enhance entity embeddings by aggregating one-hop neighbors. However, these neighbors often contain many irrelevant entities to the target relation, which introduces a large amount of noise. And existing methods are not sensitive to the semantic differences and task characteristics in the reference set, which leads to a lack of deep semantic meanings in relation representations and weakens relation inference. To address these challenges, we propose meta learning based few shot knowledge graph completion with domain selected aggregation. Specifically, the method introduces a domain-selected neighborhood aggregation mechanism that dynamically filters irrelevant neighbors through a selection strategy and a gating module, effectively suppressing noise propagation under sparse data conditions. Moreover, a relation meta-learner is designed by integrating contextual attention with a multi-layer perceptron to capture deep semantic correlations among reference triples and generate more expressive task-aware relational representations. An embedding learner further utilizes a meta-optimization strategy to enable rapid adaptation to new tasks. Experiments on NELL-One and Wiki-One datasets demonstrate that the method significantly outperforms state-of-the-art baselines. Specifically, in 5-shot tasks, it achieves performance improvements of \(1.6\%\) and \(0.9\%\) on the Hits@10 metric for datasets, respectively.