ZeroCard: Cardinality Estimation with Zero Dependence on Target Databases -- No Data, No Query, No Retraining

2025-10-09

AI Summary

Existing learning-based cardinality estimation methods heavily rely on target database data distributions or query logs, exhibiting poor generalization and limited cross-database deployability. Method: We propose ZeroCard—the first fully zero-dependency cardinality estimator that requires no access to raw data, query samples, or retraining on the target database; instead, it leverages only schema-level semantic information for cross-database transfer. Its core innovation is the first application of schema semantics modeling to cardinality estimation, featuring a query-agnostic schema encoder and a large-scale pre-trained distribution prediction model trained on real-world tables. Results: Experiments across multiple real datasets and query workloads demonstrate that ZeroCard achieves high accuracy (mean Q-error < 2.5), significantly outperforming state-of-the-art zero-shot and few-shot approaches. It enables plug-and-play deployment, eliminating costly adaptation overhead and substantially improving practical usability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Data Mining & Knowledge Management: Intelligent Query Processing
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Cardinality estimation is a fundamental task in database systems and plays a critical role in query optimization. Despite significant advances in learning-based cardinality estimation methods, most existing approaches remain difficult to generalize to new datasets due to their strong dependence on raw data or queries, thus limiting their practicality in real scenarios. To overcome these challenges, we argue that semantics in the schema may benefit cardinality estimation, and leveraging such semantics may alleviate these dependencies. To this end, we introduce ZeroCard, the first semantics-driven cardinality estimation method that can be applied without any dependence on raw data access, query logs, or retraining on the target database. Specifically, we propose to predict data distributions using schema semantics, thereby avoiding raw data dependence. Then, we introduce a query template-agnostic representation method to alleviate query dependence. Finally, we construct a large-scale query dataset derived from real-world tables and pretrain ZeroCard on it, enabling it to learn cardinality from schema semantics and predicate representations. After pretraining, ZeroCard's parameters can be frozen and applied in an off-the-shelf manner. We conduct extensive experiments to demonstrate the distinct advantages of ZeroCard and show its practical applications in query optimization. Its zero-dependence property significantly facilitates deployment in real-world scenarios.

Problem

• Estimating cardinality without target database dependencies
• Overcoming generalization limitations in learning-based methods
• Leveraging schema semantics to replace data and query reliance

Innovation

• Estimates cardinality using schema semantics without data
• Uses query-agnostic representation to avoid query dependence
• Pretrains model on large dataset for zero retraining