Scholarlink

<p>Incomplete multi-view clustering (IMVC) aims to explore complementary and consistent information across incomplete views, yet existing IMVC methods overlook the potential hidden relationships between missing data. This paper proposes an adaptive graph learning approach for incomplete multi-view inferring and clustering (IMIC-AGL), which utilizes observable information between missing views to model and infer missing data. Specifically, missing data is modeled using robust principal component analysis, and adaptive neighborhood graph learning with rank constraints is employed to effectively fill in missing data. Experiments on benchmark datasets with varying missing rates demonstrate the effectiveness of IMIC-AGL, achieving state-of-the-art clustering performance, particularly under high missing ratios.</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

Adaptive graph learning for enhanced incomplete multi-view clustering

  • 期刊论文

  • 发表日期：

    2025年4月29日

查看全文
  • Rui Hong,
  • Xiao-ping Chen,
  • Yan Zhou,
  • Hui Liu,
  • Tiancai Wan,
  • Taili Bai

摘要

Incomplete multi-view clustering (IMVC) aims to explore complementary and consistent information across incomplete views, yet existing IMVC methods overlook the potential hidden relationships between missing data. This paper proposes an adaptive graph learning approach for incomplete multi-view inferring and clustering (IMIC-AGL), which utilizes observable information between missing views to model and infer missing data. Specifically, missing data is modeled using robust principal component analysis, and adaptive neighborhood graph learning with rank constraints is employed to effectively fill in missing data. Experiments on benchmark datasets with varying missing rates demonstrate the effectiveness of IMIC-AGL, achieving state-of-the-art clustering performance, particularly under high missing ratios.