# Explaining Inference Queries with Bayesian Optimization

arXiv: https://arxiv.org/abs/2102.05308 · HTML: https://mlsanity.com/paper/2102.05308/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 56 references that are in the map.
- First posted on arXiv 10 Feb 2021.

## Builds on (most cited first, 20 of 20)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [Scalable Bayesian Optimization Using Deep Neural Networks](https://mlsanity.com/paper/1502.05700/) (2015)
- [Random Search and Reproducibility for Neural Architecture Search](https://mlsanity.com/paper/1902.07638/) (2019)
- [Combinatorial Bayesian Optimization using the Graph Cartesian Product](https://mlsanity.com/paper/1902.00448/) (2019)
- [Simple random search provides a competitive approach to reinforcement learning](https://mlsanity.com/paper/1803.07055/) (2018)
- [Automated Data Slicing for Model Validation:A Big data - AI Integration Approach](https://mlsanity.com/paper/1807.06068/) (2018)
- [Dealing with Integer-valued Variables in Bayesian Optimization with Gaussian Processes](https://mlsanity.com/paper/1706.03673/) (2017)
- [Bayesian Optimization of Combinatorial Structures](https://mlsanity.com/paper/1806.08838/) (2018)
- [Bayesian Optimisation over Multiple Continuous and Categorical Inputs](https://mlsanity.com/paper/1906.08878/) (2019)
- [Student-t Processes as Alternatives to Gaussian Processes](https://mlsanity.com/paper/1402.4306/) (2014)
- [Bayesian Optimization for Categorical and Category-Specific Continuous Inputs](https://mlsanity.com/paper/1911.12473/) (2019)
- [Complaint-driven Training Data Debugging for Query 2.0](https://mlsanity.com/paper/2004.05722/) (2020)
- [MacroBase: Prioritizing Attention in Fast Data](https://mlsanity.com/paper/1603.00567/) (2016)
- [Scalable Combinatorial Bayesian Optimization with Tractable Statistical models](https://mlsanity.com/paper/2008.08177/) (2020)
- [Explaining Aggregates for Exploratory Analytics](https://mlsanity.com/paper/1812.11346/) (2018)
- [Handling Concept Drifts in Regression Problems -- the Error Intersection Approach](https://mlsanity.com/paper/2004.00438/) (2020)
- [CADET: Debugging and Fixing Misconfigurations using Counterfactual Reasoning](https://mlsanity.com/paper/2010.06061/) (2020)

## Built on by (most cited first, 2 of 2)

- [XInsight: eXplainable Data Analysis Through The Lens of Causality](https://mlsanity.com/paper/2207.12718/) (2022)
- [Stress-Testing ML Pipelines with Adversarial Data Corruption](https://mlsanity.com/paper/2506.01230/) (2025)

## Abstract (arXiv)

Obtaining an explanation for an SQL query result can enrich the analysis experience, reveal data errors, and provide deeper insight into the data. Inference query explanation seeks to explain unexpected aggregate query results on inference data; such queries are challenging to explain because an explanation may need to be derived from the source, training, or inference data in an ML pipeline. In this paper, we model an objective function as a black-box function and propose BOExplain, a novel framework for explaining inference queries using Bayesian optimization (BO). An explanation is a predicate defining the input tuples that should be removed so that the query result of interest is significantly affected. BO - a technique for finding the global optimum of a black-box function - is used to find the best predicate. We develop two new techniques (individual contribution encoding and warm start) to handle categorical variables. We perform experiments showing that the predicates found by BOExplain have a higher degree of explanation compared to those found by the state-of-the-art query explanation engines. We also show that BOExplain is effective at deriving explanations for inference queries from source and training data on a variety of real-world datasets. BOExplain is open-sourced as a Python package at https://github.com/sfu-db/BOExplain.