2 papers
cs.DB2025
Algorithmic Complexity Attacks on All Learned Cardinality Estimators: A Data-centric Approach
Yingze Li, Xianglong Liu, Dong Wang +4
Learned cardinality estimators show promise in query cardinality prediction, yet they universally exhibit fragility to training data drifts, posing risks for real-world deployment.…
cs.DB2024
Updateable Data-Driven Cardinality Estimator with Bounded Q-error
Yingze Li, Xianglong Liu, Hongzhi Wang +2
Modern Cardinality Estimators struggle with data updates. This research tackles this challenge within single-table. We introduce ICE, an Index-based Cardinality Estimator, the firs…