# Plan-Structured Deep Neural Network Models for Query Performance Prediction

arXiv: https://arxiv.org/abs/1902.00132 · HTML: https://mlsanity.com/paper/1902.00132/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2019.

## Built on by (most cited first, 24 of 24)

- [Lero: A Learning-to-Rank Query Optimizer](https://mlsanity.com/paper/2302.06873/) (2023)
- [Zero-Shot Cost Models for Out-of-the-box Learned Cost Prediction](https://mlsanity.com/paper/2201.00561/) (2022)
- [A Survey on Advancing the DBMS Query Optimizer: Cardinality Estimation, Cost Model, and Plan Enumeration](https://mlsanity.com/paper/2101.01507/) (2021)
- [FactorJoin: A New Cardinality Estimation Framework for Join Queries](https://mlsanity.com/paper/2212.05526/) (2022)
- [A Unified Transferable Model for ML-Enhanced DBMS](https://mlsanity.com/paper/2105.02418/) (2021)
- [One Model to Rule them All: Towards Zero-Shot Learning for Databases](https://mlsanity.com/paper/2105.00642/) (2021)
- [Deep Configuration Performance Learning: A Systematic Survey and Taxonomy](https://mlsanity.com/paper/2403.03322/) (2024)
- [Forecasting SQL Query Cost at Twitter](https://mlsanity.com/paper/2204.05529/) (2022)
- [Database Workload Characterization with Query Plan Encoders](https://mlsanity.com/paper/2105.12287/) (2021)
- [Dividable Configuration Performance Learning](https://mlsanity.com/paper/2409.07629/) (2024)
- [Learned Graph Rewriting with Equality Saturation: A New Paradigm in Relational Query Rewrite and Beyond](https://mlsanity.com/paper/2407.12794/) (2024)
- [ML-Powered Index Tuning: An Overview of Recent Progress and Open Challenges](https://mlsanity.com/paper/2308.13641/) (2023)
- [Phoebe: A Learning-based Checkpoint Optimizer](https://mlsanity.com/paper/2110.02313/) (2021)
- [CAMAL: Optimizing LSM-trees via Active Learning](https://mlsanity.com/paper/2409.15130/) (2024)
- [DistJoin: A Decoupled Join Cardinality Estimator based on Adaptive Neural Predicate Modulation](https://mlsanity.com/paper/2503.08994/) (2025)
- [Neural-based Modeling for Performance Tuning of Spark Data Analytics](https://mlsanity.com/paper/2101.08167/) (2021)
- [Learning GraphQL Query Costs (Extended Version)](https://mlsanity.com/paper/2108.11139/) (2021)
- [LearnedWMP: Workload Memory Prediction Using Distribution of Query Templates](https://mlsanity.com/paper/2401.12103/) (2024)
- [Compositional Models for Estimating Causal Effects](https://mlsanity.com/paper/2406.17714/) (2024)
- [CONCERTO: Complex Query Execution Mechanism-Aware Learned Cost Estimation](https://mlsanity.com/paper/2412.00749/) (2024)
- [Selective Use of Yannakakis' Algorithm to Improve Query Performance: Machine Learning to the Rescue](https://mlsanity.com/paper/2502.20233/) (2025)
- [LLM4Hint: Leveraging Large Language Models for Hint Recommendation in Offline Query Optimization](https://mlsanity.com/paper/2507.03384/) (2025)
- [VQPP: Video Query Performance Prediction Benchmark](https://mlsanity.com/paper/2602.17814/) (2026)
- [Agentic Cost-Aware Query Planning with Knowledge Distillation for Big Data Analytics](https://mlsanity.com/paper/2605.17831/) (2026)

## Abstract (arXiv)

Query performance prediction, the task of predicting the latency of a query, is one of the most challenging problem in database management systems. Existing approaches rely on features and performance models engineered by human experts, but often fail to capture the complex interactions between query operators and input relations, and generally do not adapt naturally to workload characteristics and patterns in query execution plans. In this paper, we argue that deep learning can be applied to the query performance prediction problem, and we introduce a novel neural network architecture for the task: a plan-structured neural network. Our approach eliminates the need for human-crafted feature selection and automatically discovers complex performance models both at the operator and query plan level. Our novel neural network architecture can match the structure of any optimizer-selected query execution plan and predict its latency with high accuracy. We also propose a number of optimizations that reduce training overhead without sacrificing effectiveness. We evaluated our techniques on various workloads and we demonstrate that our plan-structured neural network can outperform the state-of-the-art in query performance prediction.