Tree of Concepts: Interpretable Continual Learners in Non-Stationary Clinical Domains

TL;DR

The paper introduces Tree of Concepts, an interpretable continual learning framework using decision trees and concept bottleneck models to maintain stability and interpretability in healthcare applications under distribution shifts.

Contribution

It proposes a novel method combining decision trees with concept bottleneck models for stable, interpretable continual learning in non-stationary domains.

Findings

Outperforms existing methods in stability-plasticity trade-off on healthcare benchmarks.

Maintains consistent explanations across sequential updates.

Supports continual adaptation while preserving interpretability.

Abstract

Continual learning aims to update models under distribution shift without forgetting, yet many high-stakes deployments, such as healthcare, also require interpretability. In practice, models that adapt well (e.g., deep networks) are often opaque, while models that are interpretable (e.g., decision trees) are brittle under shift, making it difficult to achieve both properties simultaneously. In response, we propose Tree of Concepts, an interpretable continual learning framework that uses a shallow decision tree to define a fixed, rule-based concept interface and trains a concept bottleneck model to predict these concepts from raw features. Continual updates act on the concept extractor and label head while keeping concept semantics stable over time, yielding explanations that do not drift across sequential updates. On multiple tabular healthcare benchmarks under continual learning protocols, our method achieves a stronger stability-plasticity trade-off than existing baselines, including replay-enhanced variants. Our results suggest that structured concept interfaces can support continual adaptation while preserving a consistent audit interface in non-stationary, high-stakes domains.