# Feature graphs for interpretable unsupervised tree ensembles: centrality, interaction, and application in disease subtyping

arXiv: https://arxiv.org/abs/2404.17886 · HTML: https://mlsanity.com/paper/2404.17886/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 66 references that are in the map.
- First posted on arXiv 27 Apr 2024.

## Builds on (most cited first, 9 of 9)

- [From Clustering to Cluster Explanations via Neural Networks](https://mlsanity.com/paper/1906.07633/) (2019)
- [A framework for benchmarking clustering algorithms](https://mlsanity.com/paper/2209.09493/) (2022)
- [A graph-embedded deep feedforward network for disease outcome classification and feature selection using gene expression data](https://mlsanity.com/paper/1801.06202/) (2018)
- [Parea: multi-view ensemble clustering for cancer subtype discovery](https://mlsanity.com/paper/2209.15399/) (2022)
- [How Many Dissimilarity/Kernel Self Organizing Map Variants Do We Need?](https://mlsanity.com/paper/1407.0611/) (2014)
- [A Class-Aware Representation Refinement Framework for Graph Classification](https://mlsanity.com/paper/2209.00936/) (2022)
- [Graph-guided random forest for gene set selection](https://mlsanity.com/paper/2108.11674/) (2021)
- [Hierarchical clustering: visualization, feature importance and model selection](https://mlsanity.com/paper/2112.01372/) (2021)
- [Federated unsupervised random forest for privacy-preserving patient stratification](https://mlsanity.com/paper/2401.16094/) (2024)

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

- [Surrogate Interpretable Graph for Random Decision Forests](https://mlsanity.com/paper/2506.01988/) (2025)

## Abstract (arXiv)

Interpretable machine learning has emerged as central in leveraging artificial intelligence within high-stakes domains such as healthcare, where understanding the rationale behind model predictions is as critical as achieving high predictive accuracy. In this context, feature selection assumes a pivotal role in enhancing model interpretability by identifying the most important input features in black-box models. While random forests are frequently used in biomedicine for their remarkable performance on tabular datasets, the accuracy gained from aggregating decision trees comes at the expense of interpretability. Consequently, feature selection for enhancing interpretability in random forests has been extensively explored in supervised settings. However, its investigation in the unsupervised regime remains notably limited. To address this gap, the study introduces novel methods to construct feature graphs from unsupervised random forests and feature selection strategies to derive effective feature combinations from these graphs. Feature graphs are constructed for the entire dataset as well as individual clusters leveraging the parent-child node splits within the trees, such that feature centrality captures their relevance to the clustering task, while edge weights reflect the discriminating power of feature pairs. Graph-based feature selection methods are extensively evaluated on synthetic and benchmark datasets both in terms of their ability to reduce dimensionality while improving clustering performance, as well as to enhance model interpretability. An application on omics data for disease subtyping identifies the top features for each cluster, showcasing the potential of the proposed approach to enhance interpretability in clustering analyses and its utility in a real-world biomedical application.