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

• URL: http://arxiv.org/abs/2604.17089v1
• Date: Sat, 18 Apr 2026 17:58:37 GMT
• Title: Tree of Concepts: Interpretable Continual Learners in Non-Stationary Clinical Domains
• Abstract summary: Continual learning aims to update models under distribution shift without forgetting, yet many high-stakes deployments, such as healthcare, also require interpretability.<n>We propose Tree of Concepts, an interpretable continual learning framework that uses a shallow decision tree to define a fixed, rule-based concept interface.<n>Our results suggest that structured concept interfaces can support continual adaptation while preserving a consistent audit interface in non-stationary, high-stakes domains.
• Score: 2.688900425133985
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• ConceptTS: LLM-Guided Concept Bottlenecks for Interpretable Multivariate Time-Series Forecasting [5.864483407118622]
  ConceptTS is an interpretable forecasting framework that organizes its predictions around named, human-readable concepts.<n>A shared decoder combines representations derived from their predicted activations to construct the forecast.<n>Experiments on the Beijing Multi-Site Air Quality dataset show that ConceptTS achieves accuracy competitive with strong black-box baselines.
  arXiv  Detail & Related papers  (2026-08-21T16:35:44Z)
• Concept Flow Models: Anchoring Concept-Based Reasoning with Hierarchical Bottlenecks [4.944427102119257]
  Concept Bottleneck Models (CBMs) enhance interpretability by projecting learned features into a human-understandable concept space.<n>Recent approaches leverage vision-language models to generate concept embeddings, reducing the need for manual concept annotations.<n>We propose Concept Flow Models (CFMs), which replace the flat bottleneck with a hierarchical, concept-driven decision tree.
  arXiv  Detail & Related papers  (2026-06-17T18:27:17Z)
• CPC-VAR:Continual Personalized and Compositional Generation in Visual Autoregressive Models [69.9266117908314]
  Visual autoregressive ( VAR) models have emerged as efficient paradigm for text-to-image generation.<n>Existing VAR-based personalization methods fail to accommodate evolving user demands.<n>We present the first systematic study of continual personalized generation in VAR models.
  arXiv  Detail & Related papers  (2026-05-19T12:18:15Z)
• Hyperbolic Concept Bottleneck Models [17.962222104908648]
  Concept Bottleneck Models (CBMs) have become a popular approach to enable interpretability in neural networks by constraining inputs to a set of human-understandable concepts.<n>We propose Hyperbolic Concept Bottleneck Models (HypCBM), a post-hoc framework that grounds the bottleneck in this structure by reformulating concept activation as asymmetric geometric containment in hyperbolic space.<n>We show they encode a natural test-time activation signal: the margin of inclusion within a concept's entailment cone yields sparse, hierarchy-aware activations without any additional supervision or learned modules.
  arXiv  Detail & Related papers  (2026-05-07T15:41:22Z)
• Insight: Interpretable Semantic Hierarchies in Vision-Language Encoders [52.94006363830628]
  Language-aligned vision foundation models perform strongly across diverse downstream tasks.<n>Recent works decompose these representations into human-interpretable concepts, but provide poor spatial grounding and are limited to image classification tasks.<n>We propose Insight, a language-aligned concept foundation model that provides fine-grained concepts, which are human-interpretable and spatially grounded in the input image.
  arXiv  Detail & Related papers  (2026-01-20T09:57:26Z)
• Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions [70.87254264798341]
  PCI is a training-free and model-agnostic framework for analyzing concept dynamics through diffusion time.<n>It reveals diverse temporal behaviors across diffusion models, in which certain phases of the trajectory are more favorable to specific concepts even within the same concept type.
  arXiv  Detail & Related papers  (2025-12-09T11:05:08Z)
• When, How Long and How Much? Interpretable Neural Networks for Time Series Regression by Learning to Mask and Aggregate [16.533105886716804]
  Time series extrinsic regression (TSER) refers to the task of predicting a continuous target variable from an input time series.<n>New approach learns a compact set of human-understandable concepts without requiring any annotations.
  arXiv  Detail & Related papers  (2025-12-03T09:01:41Z)
• FaCT: Faithful Concept Traces for Explaining Neural Network Decisions [56.796533084868884]
  Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge.<n>We put emphasis on the faithfulness of concept-based explanations and propose a new model with model-inherent mechanistic concept-explanations.<n>Our concepts are shared across classes and, from any layer, their contribution to the logit and their input-visualization can be faithfully traced.
  arXiv  Detail & Related papers  (2025-10-29T13:35:46Z)
• ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation [3.7816957214446103]
  ConceptGuard is a comprehensive approach that combines shift embedding, concept-binding prompts and memory preservation regularization.<n>We show that our approach outperforms all the baseline methods consistently and significantly in both quantitative and qualitative analyses.
  arXiv  Detail & Related papers  (2025-03-13T13:39:24Z)
• Concept Based Continuous Prompts for Interpretable Text Classification [18.821639956791213]
  We propose a framework for interpreting continuous prompts by decomposing them into human-readable concepts.<n>We employ GPT-4o to generate a concept pool and choose potential candidate concepts that are discriminative and representative.<n>Experiments demonstrate that our framework can achieve similar results as the original P-tuning and word-based approaches.
  arXiv  Detail & Related papers  (2024-12-02T15:56:08Z)
• How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization? [91.49559116493414]
  We propose a novel Concept-Incremental text-to-image Diffusion Model (CIDM) It can resolve catastrophic forgetting and concept neglect to learn new customization tasks in a concept-incremental manner. Experiments validate that our CIDM surpasses existing custom diffusion models.
  arXiv  Detail & Related papers  (2024-10-23T06:47:29Z)
• WormKAN: Are KAN Effective for Identifying and Tracking Concept Drift in Time Series? [6.4314326272535896]
  WormKAN is a concept-aware KAN-based model to address concept drift in co-evolving time series.<n>WormKAN consists of three key components: Patch Normalization, Temporal Representation Module, and Concept Dynamics.
  arXiv  Detail & Related papers  (2024-10-13T23:05:37Z)
• Enforcing Interpretability in Time Series Transformers: A Concept Bottleneck Framework [2.8470354623829577]
  We develop a framework based on Concept Bottleneck Models to enforce interpretability of time series Transformers. We modify the training objective to encourage a model to develop representations similar to predefined interpretable concepts. We find that the model performance remains mostly unaffected, while the model shows much improved interpretability.
  arXiv  Detail & Related papers  (2024-10-08T14:22:40Z)
• ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance [90.57708419344007]
  We present **ClassDiffusion**, a technique that leverages a **semantic preservation loss** to explicitly regulate the concept space when learning a new concept.<n>Although simple, this approach effectively prevents semantic drift during the fine-tuning process of the target concepts.
  arXiv  Detail & Related papers  (2024-05-27T17:50:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.