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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cho, Dongkyu, Li, Xiyue, Adhikari, Samrachana, Chunara, Rumi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911604488011776
author Cho, Dongkyu
Li, Xiyue
Adhikari, Samrachana
Chunara, Rumi
author_facet Cho, Dongkyu
Li, Xiyue
Adhikari, Samrachana
Chunara, Rumi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_17089
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Tree of Concepts: Interpretable Continual Learners in Non-Stationary Clinical Domains
Cho, Dongkyu
Li, Xiyue
Adhikari, Samrachana
Chunara, Rumi
Machine Learning
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.
title Tree of Concepts: Interpretable Continual Learners in Non-Stationary Clinical Domains
topic Machine Learning
url https://arxiv.org/abs/2604.17089