# Model Learning with Personalized Interpretability Estimation (ML-PIE)

arXiv: https://arxiv.org/abs/2104.06060 · HTML: https://mlsanity.com/paper/2104.06060/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 63 references that are in the map.
- First posted on arXiv 13 Apr 2021.

## Builds on (most cited first, 22 of 22)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model](https://mlsanity.com/paper/1511.01644/) (2015)
- [Supersparse Linear Integer Models for Optimized Medical Scoring Systems](https://mlsanity.com/paper/1502.04269/) (2015)
- [Falling Rule Lists](https://mlsanity.com/paper/1411.5899/) (2014)
- [On Explaining Decision Trees](https://mlsanity.com/paper/2010.11034/) (2020)
- [Interpretable Policies for Reinforcement Learning by Genetic Programming](https://mlsanity.com/paper/1712.04170/) (2017)
- [GLocalX -- From Local to Global Explanations of Black Box AI Models](https://mlsanity.com/paper/2101.07685/) (2021)
- [Active Learning Using Uncertainty Information](https://mlsanity.com/paper/1702.08540/) (2017)
- [Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization](https://mlsanity.com/paper/2102.04523/) (2021)
- [Evolutionary learning of interpretable decision trees](https://mlsanity.com/paper/2012.07723/) (2020)
- [Learning a Formula of Interpretability to Learn Interpretable Formulas](https://mlsanity.com/paper/2004.11170/) (2020)
- [Interpretable Two-level Boolean Rule Learning for Classification](https://mlsanity.com/paper/1511.07361/) (2015)
- [On Explaining Machine Learning Models by Evolving Crucial and Compact Features](https://mlsanity.com/paper/1907.02260/) (2019)
- [Genetic Programming for Evolving a Front of Interpretable Models for Data Visualisation](https://mlsanity.com/paper/2001.09578/) (2020)
- [Fast methods for training Gaussian processes on large data sets](https://mlsanity.com/paper/1604.01250/) (2016)
- [Morphology dictates a robot's ability to ground crowd-proposed language](https://mlsanity.com/paper/1712.05881/) (2017)
- [Mining Feature Relationships in Data](https://mlsanity.com/paper/2102.01355/) (2021)

## Built on by (most cited first, 9 of 9)

- [Symbolic Regression is NP-hard](https://mlsanity.com/paper/2207.01018/) (2022)
- [On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbations](https://mlsanity.com/paper/2201.09051/) (2022)
- [Seven challenges for harmonizing explainability requirements](https://mlsanity.com/paper/2108.05390/) (2021)
- [Differentiable Genetic Programming for High-dimensional Symbolic Regression](https://mlsanity.com/paper/2304.08915/) (2023)
- [Biological and Radiological Dictionary of Radiomics Features: Addressing Understandable AI Issues in Personalized Prostate Cancer; Dictionary Version PM1.0](https://mlsanity.com/paper/2412.10967/) (2024)
- [Evolutionary Computation and Explainable AI: A Roadmap to Understandable Intelligent Systems](https://mlsanity.com/paper/2406.07811/) (2024)
- [Interpretable Non-linear Survival Analysis with Evolutionary Symbolic Regression](https://mlsanity.com/paper/2504.05756/) (2025)
- [Evo* 2023 -- Late-Breaking Abstracts Volume](https://mlsanity.com/paper/2403.13950/) (2024)
- [Pathobiological Dictionary Defining Pathomics and Texture Features: Addressing Understandable AI Issues in Personalized Liver Cancer; Dictionary Version LCP1.0](https://mlsanity.com/paper/2505.14926/) (2025)

## Abstract (arXiv)

High-stakes applications require AI-generated models to be interpretable. Current algorithms for the synthesis of potentially interpretable models rely on objectives or regularization terms that represent interpretability only coarsely (e.g., model size) and are not designed for a specific user. Yet, interpretability is intrinsically subjective. In this paper, we propose an approach for the synthesis of models that are tailored to the user by enabling the user to steer the model synthesis process according to her or his preferences. We use a bi-objective evolutionary algorithm to synthesize models with trade-offs between accuracy and a user-specific notion of interpretability. The latter is estimated by a neural network that is trained concurrently to the evolution using the feedback of the user, which is collected using uncertainty-based active learning. To maximize usability, the user is only asked to tell, given two models at the time, which one is less complex. With experiments on two real-world datasets involving 61 participants, we find that our approach is capable of learning estimations of interpretability that can be very different for different users. Moreover, the users tend to prefer models found using the proposed approach over models found using non-personalized interpretability indices.