# Surrogate Interpretable Graph for Random Decision Forests

arXiv: https://arxiv.org/abs/2506.01988 · HTML: https://mlsanity.com/paper/2506.01988/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 56 references that are in the map.
- First posted on arXiv 17 May 2025.

## Builds on (most cited first, 23 of 23)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Generalized Random Forests](https://mlsanity.com/paper/1610.01271/) (2016)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Iterative Random Forests to detect predictive and stable high-order interactions](https://mlsanity.com/paper/1706.08457/) (2017)
- [On Representing Linear Programs by Graph Neural Networks](https://mlsanity.com/paper/2209.12288/) (2022)
- [Interpreting Tree Ensembles with inTrees](https://mlsanity.com/paper/1408.5456/) (2014)
- [Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles](https://mlsanity.com/paper/2401.12069/) (2024)
- [Towards Foundation Models for Mixed Integer Linear Programming](https://mlsanity.com/paper/2410.08288/) (2024)
- [Geometry- and Accuracy-Preserving Random Forest Proximities](https://mlsanity.com/paper/2201.12682/) (2022)
- [Interpretable Random Forests via Rule Extraction](https://mlsanity.com/paper/2004.14841/) (2020)
- [A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability](https://mlsanity.com/paper/2310.02807/) (2023)
- [Hierarchical Shrinkage: improving the accuracy and interpretability of tree-based methods](https://mlsanity.com/paper/2202.00858/) (2022)
- [Connecting Interpretability and Robustness in Decision Trees through Separation](https://mlsanity.com/paper/2102.07048/) (2021)
- [Learning Interpretable Rules for Scalable Data Representation and Classification](https://mlsanity.com/paper/2310.14336/) (2023)
- [Trained Random Forests Completely Reveal your Dataset](https://mlsanity.com/paper/2402.19232/) (2024)
- [Explaining Random Forests using Bipolar Argumentation and Markov Networks (Technical Report)](https://mlsanity.com/paper/2211.11699/) (2022)
- [A Framework for Inherently Interpretable Optimization Models](https://mlsanity.com/paper/2208.12570/) (2022)
- [A Nested Model for AI Design and Validation](https://mlsanity.com/paper/2407.16888/) (2024)
- [AI Readiness in Healthcare through Storytelling XAI](https://mlsanity.com/paper/2410.18725/) (2024)
- [Deep graph matching meets mixed-integer linear programming: Relax at your own risk ?](https://mlsanity.com/paper/2108.00394/) (2021)
- [Forest-ORE: Mining Optimal Rule Ensemble to interpret Random Forest models](https://mlsanity.com/paper/2403.17588/) (2024)
- [Feature graphs for interpretable unsupervised tree ensembles: centrality, interaction, and application in disease subtyping](https://mlsanity.com/paper/2404.17886/) (2024)

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

- [UbiQTree: Uncertainty Quantification in XAI with Tree Ensembles](https://mlsanity.com/paper/2508.09639/) (2025)

## Abstract (arXiv)

The field of health informatics has been profoundly influenced by the development of random forest models, which have led to significant advances in the interpretability of feature interactions. These models are characterized by their robustness to overfitting and parallelization, making them particularly useful in this domain. However, the increasing number of features and estimators in random forests can prevent domain experts from accurately interpreting global feature interactions, thereby compromising trust and regulatory compliance. A method called the surrogate interpretability graph has been developed to address this issue. It uses graphs and mixed-integer linear programming to analyze and visualize feature interactions. This improves their interpretability by visualizing the feature usage per decision-feature-interaction table and the most dominant hierarchical decision feature interactions for predictions. The implementation of a surrogate interpretable graph enhances global interpretability, which is critical for such a high-stakes domain.