# Decision Predicate Graphs: Enhancing Interpretability in Tree Ensembles

arXiv: https://arxiv.org/abs/2404.02942 · HTML: https://mlsanity.com/paper/2404.02942/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 42 references that are in the map.
- First posted on arXiv 3 Apr 2024.

## Builds on (most cited first, 10 of 10)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Interpreting Tree Ensembles with inTrees](https://mlsanity.com/paper/1408.5456/) (2014)
- [Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach](https://mlsanity.com/paper/1606.09066/) (2016)
- [Explainable Matrix -- Visualization for Global and Local Interpretability of Random Forest Classification Ensembles](https://mlsanity.com/paper/2005.04289/) (2020)
- [Interpreting Models via Single Tree Approximation](https://mlsanity.com/paper/1610.09036/) (2016)
- [Optimal Decision Diagrams for Classification](https://mlsanity.com/paper/2205.14500/) (2022)
- [Decision Stream: Cultivating Deep Decision Trees](https://mlsanity.com/paper/1704.07657/) (2017)
- [Tree in Tree: from Decision Trees to Decision Graphs](https://mlsanity.com/paper/2110.00392/) (2021)
- [BELLATREX: Building Explanations through a LocaLly AccuraTe Rule EXtractor](https://mlsanity.com/paper/2203.15511/) (2022)

## Built on by (most cited first, 5 of 5)

- [Extending Decision Predicate Graphs for Comprehensive Explanation of Isolation Forest](https://mlsanity.com/paper/2505.04019/) (2025)
- [Upside-Down Reinforcement Learning for More Interpretable Optimal Control](https://mlsanity.com/paper/2411.11457/) (2024)
- [Explaining AutoClustering: Uncovering Meta-Feature Contribution in AutoML for Clustering](https://mlsanity.com/paper/2602.18348/) (2026)
- [Close to Reality: Interpretable and Feasible Data Augmentation for Imbalanced Learning](https://mlsanity.com/paper/2603.13927/) (2026)
- [Spectral Model eXplainer: a chemically-grounded explainability framework for spectral-based machine learning models](https://mlsanity.com/paper/2605.02684/) (2026)

## Abstract (arXiv)

Understanding the decisions of tree-based ensembles and their relationships is pivotal for machine learning model interpretation. Recent attempts to mitigate the human-in-the-loop interpretation challenge have explored the extraction of the decision structure underlying the model taking advantage of graph simplification and path emphasis. However, while these efforts enhance the visualisation experience, they may either result in a visually complex representation or compromise the interpretability of the original ensemble model. In addressing this challenge, especially in complex scenarios, we introduce the Decision Predicate Graph (DPG) as a model-agnostic tool to provide a global interpretation of the model. DPG is a graph structure that captures the tree-based ensemble model and learned dataset details, preserving the relations among features, logical decisions, and predictions towards emphasising insightful points. Leveraging well-known graph theory concepts, such as the notions of centrality and community, DPG offers additional quantitative insights into the model, complementing visualisation techniques, expanding the problem space descriptions, and offering diverse possibilities for extensions. Empirical experiments demonstrate the potential of DPG in addressing traditional benchmarks and complex classification scenarios.