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

arXiv: https://arxiv.org/abs/2604.17089 · HTML: https://mlsanity.com/paper/2604.17089/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Builds on (most cited first, 19 of 19)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [FOSTER: Feature Boosting and Compression for Class-Incremental Learning](https://mlsanity.com/paper/2204.04662/) (2022)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery](https://mlsanity.com/paper/2407.14499/) (2024)
- [Computationally Budgeted Continual Learning: What Does Matter?](https://mlsanity.com/paper/2303.11165/) (2023)
- [Language Guided Concept Bottleneck Models for Interpretable Continual Learning](https://mlsanity.com/paper/2503.23283/) (2025)
- [How Efficient Are Today's Continual Learning Algorithms?](https://mlsanity.com/paper/2303.18171/) (2023)
- [Integrating Clinical Knowledge into Concept Bottleneck Models](https://mlsanity.com/paper/2407.06600/) (2024)
- [Connecting Interpretability and Robustness in Decision Trees through Separation](https://mlsanity.com/paper/2102.07048/) (2021)
- [Forget Forgetting: Continual Learning in a World of Abundant Memory](https://mlsanity.com/paper/2502.07274/) (2025)
- [Continual Learning in Medical Imaging: A Survey and Practical Analysis](https://mlsanity.com/paper/2405.13482/) (2024)
- [Bridging Streaming Continual Learning via In-Context Large Tabular Models](https://mlsanity.com/paper/2512.11668/) (2025)
- [Overcoming Catastrophic Forgetting in Tabular Data Classification: A Pseudorehearsal-based approach](https://mlsanity.com/paper/2407.09039/) (2024)
- [Correct Reasoning Paths Visit Shared Decision Pivots](https://mlsanity.com/paper/2509.21549/) (2025)

## Built on by (most cited first, 2 of 2)

- [Continual Learning via Self-Probe Gradients](https://mlsanity.com/paper/2609.32771/) (2026)
- [Self-Preservation in Language Models](https://mlsanity.com/paper/2610.12602/) (2026)

## Abstract (arXiv)

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.