# Interpretable Differencing of Machine Learning Models

arXiv: https://arxiv.org/abs/2306.06473 · HTML: https://mlsanity.com/paper/2306.06473/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 10 Jun 2023.

## Builds on (most cited first, 17 of 17)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [Distilling a Neural Network Into a Soft Decision Tree](https://mlsanity.com/paper/1711.09784/) (2017)
- [Unifying distillation and privileged information](https://mlsanity.com/paper/1511.03643/) (2015)
- [Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model](https://mlsanity.com/paper/1511.01644/) (2015)
- [Should we really use post-hoc tests based on mean-ranks?](https://mlsanity.com/paper/1505.02288/) (2015)
- [Boolean Decision Rules via Column Generation](https://mlsanity.com/paper/1805.09901/) (2018)
- [Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making](https://mlsanity.com/paper/1903.10598/) (2019)
- [Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation](https://mlsanity.com/paper/1710.06169/) (2017)
- [Interpretability via Model Extraction](https://mlsanity.com/paper/1706.09773/) (2017)
- [Robust Decision Trees Against Adversarial Examples](https://mlsanity.com/paper/1902.10660/) (2019)
- [Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks](https://mlsanity.com/paper/1906.03526/) (2019)
- [Connecting Interpretability and Robustness in Decision Trees through Separation](https://mlsanity.com/paper/2102.07048/) (2021)
- [Identifying Significant Predictive Bias in Classifiers](https://mlsanity.com/paper/1611.08292/) (2016)
- [Fairer and more accurate, but for whom?](https://mlsanity.com/paper/1707.00046/) (2017)
- [Model change detection with application to machine learning](https://mlsanity.com/paper/1811.07957/) (2018)

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

- [Bias Detection via Maximum Subgroup Discrepancy](https://mlsanity.com/paper/2502.02221/) (2025)

## Abstract (arXiv)

Understanding the differences between machine learning (ML) models is of interest in scenarios ranging from choosing amongst a set of competing models, to updating a deployed model with new training data. In these cases, we wish to go beyond differences in overall metrics such as accuracy to identify where in the feature space do the differences occur. We formalize this problem of model differencing as one of predicting a dissimilarity function of two ML models' outputs, subject to the representation of the differences being human-interpretable. Our solution is to learn a Joint Surrogate Tree (JST), which is composed of two conjoined decision tree surrogates for the two models. A JST provides an intuitive representation of differences and places the changes in the context of the models' decision logic. Context is important as it helps users to map differences to an underlying mental model of an AI system. We also propose a refinement procedure to increase the precision of a JST. We demonstrate, through an empirical evaluation, that such contextual differencing is concise and can be achieved with no loss in fidelity over naive approaches.