Expanding Data-Agnostic Pivotal Instances Selection Models with Proximity Trees and Ensemble Learning

2026-07-29

AI Summary

This work addresses the limited interpretability of existing machine learning methods in complex decision-making, which struggle to emulate human reasoning based on representative exemplars. To bridge this gap, the paper proposes a similarity-based hierarchical interpretable model that constructs predictions using an extremely small set of carefully selected pivotal instances. It uniquely integrates pivot selection with nearest-neighbor trees, oblique trees, and ensemble learning, establishing a data-modality-agnostic paradigm for highly interpretable modeling. Leveraging pretrained networks to uniformly process multimodal inputs—including tabular data, text, images, and time series—the method significantly outperforms current instance selection approaches across multiple benchmark datasets while achieving performance on par with state-of-the-art interpretable models.

Abstract

As decision-making processes grow more complex, machine learning tools have become essential for tackling business and societal challenges. However, many existing methods rely on decision-making procedures that are difficult to interpret. Since humans naturally make decisions by comparing new cases with a few representative examples, we aim to design an approach that selects such pivots to construct an interpretable predictive model. Inspired by decision trees, we propose a hierarchical, interpretable-by-design pivot selection model based on the similarity between pivots and input instances. Our method functions both as a pivot selection technique and a standalone predictive model. Extending beyond single pivots, we incorporate pairs of pivots that are used by proximity and oblique trees, as well as ensembles, which enhance the versatility and effectiveness of our proposal. Additionally, our approach is data modality-agnostic, leveraging pre-trained networks for data transformation. Experiments across diverse datasets, including tabular data, text, images, and time series, demonstrate the effectiveness of our approach, outperforming alternative instance selection strategies and achieving competitive results against state-of-the-art interpretable models while maintaining a minimal number of pivots.

Problem

• interpretable machine learning
• pivotal instance selection
• decision interpretability
• data-agnostic modeling
• instance-based reasoning

Innovation

• pivot selection
• proximity trees
• ensemble learning
• interpretable models
• data-agnostic