# AutoSlicer: Scalable Automated Data Slicing for ML Model Analysis

arXiv: https://arxiv.org/abs/2212.09032 · HTML: https://mlsanity.com/paper/2212.09032/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 28 references that are in the map.
- First posted on arXiv 18 Dec 2022.

## Builds on (most cited first, 11 of 11)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees](https://mlsanity.com/paper/1806.06055/) (2018)
- [Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models](https://mlsanity.com/paper/1808.00196/) (2018)
- [Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices](https://mlsanity.com/paper/1909.06349/) (2019)
- [OmniFair: A Declarative System for Model-Agnostic Group Fairness in Machine Learning](https://mlsanity.com/paper/2103.09055/) (2021)

## Built on by (most cited first, 1 of 1)

- [What to Test Next: Interpretable Coverage Gap Discovery in Driving VLMs](https://mlsanity.com/paper/2606.01624/) (2026)

## Abstract (arXiv)

Automated slicing aims to identify subsets of evaluation data where a trained model performs anomalously. This is an important problem for machine learning pipelines in production since it plays a key role in model debugging and comparison, as well as the diagnosis of fairness issues. Scalability has become a critical requirement for any automated slicing system due to the large search space of possible slices and the growing scale of data. We present Autoslicer, a scalable system that searches for problematic slices through distributed metric computation and hypothesis testing. We develop an efficient strategy that reduces the search space through pruning and prioritization. In the experiments, we show that our search strategy finds most of the anomalous slices by inspecting a small portion of the search space.