Scholarlink

Cardinality estimation is crucial for query optimization, but traditional methods struggle with complex queries. We propose LW-CQ, a lightweight machine learning-based algorithm that improves cardinality estimation for complex queries by enhancing the LW-XGB method. LW-CQ introduces four feature-level improvements and extends support for disjunctive queries and LIKE predicates. Experimental results show that LW-CQ achieves competitive accuracy while significantly reducing training and inference time, making it a promising solution for real-world database applications.

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

LW-CQ: ML-Driven Cardinality Estimation for Complex Queries

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Jiye Qiu,
  • DongHua Yang,
  • Mengmeng Li,
  • Haifeng Guo,
  • Hongqiang Wang,
  • Hongzhi Wang

摘要

Cardinality estimation is crucial for query optimization, but traditional methods struggle with complex queries. We propose LW-CQ, a lightweight machine learning-based algorithm that improves cardinality estimation for complex queries by enhancing the LW-XGB method. LW-CQ introduces four feature-level improvements and extends support for disjunctive queries and LIKE predicates. Experimental results show that LW-CQ achieves competitive accuracy while significantly reducing training and inference time, making it a promising solution for real-world database applications.