# Distilling BlackBox to Interpretable models for Efficient Transfer Learning

arXiv: https://arxiv.org/abs/2305.17303 · HTML: https://mlsanity.com/paper/2305.17303/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 26 May 2023.

## Builds on (most cited first, 17 of 17)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning](https://mlsanity.com/paper/1711.05225/) (2017)
- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [RadGraph: Extracting Clinical Entities and Relations from Radiology Reports](https://mlsanity.com/paper/2106.14463/) (2021)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Entity, Relation, and Event Extraction with Contextualized Span Representations](https://mlsanity.com/paper/1909.03546/) (2019)
- [Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off](https://mlsanity.com/paper/2209.09056/) (2022)
- [Entropy-based Logic Explanations of Neural Networks](https://mlsanity.com/paper/2106.06804/) (2021)
- [Growing a Brain: Fine-Tuning by Increasing Model Capacity](https://mlsanity.com/paper/1907.07844/) (2019)
- [Global and Local Interpretability for Cardiac MRI Classification](https://mlsanity.com/paper/1906.06188/) (2019)
- [Anatomy-Guided Weakly-Supervised Abnormality Localization in Chest X-rays](https://mlsanity.com/paper/2206.12704/) (2022)
- [Selective Prediction via Training Dynamics](https://mlsanity.com/paper/2205.13532/) (2022)
- [Tackling Shortcut Learning in Deep Neural Networks: An Iterative Approach with Interpretable Models](https://mlsanity.com/paper/2302.10289/) (2023)

## Built on by (most cited first, 4 of 4)

- [Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations](https://mlsanity.com/paper/2401.14142/) (2024)
- [FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks](https://mlsanity.com/paper/2505.17883/) (2025)
- [Selecting Feature Interactions for Generalized Additive Models by Distilling Foundation Models](https://mlsanity.com/paper/2604.13332/) (2026)
- [Distributionally robust self-supervised learning for tabular data](https://mlsanity.com/paper/2410.08511/) (2024)

## Abstract (arXiv)

Building generalizable AI models is one of the primary challenges in the healthcare domain. While radiologists rely on generalizable descriptive rules of abnormality, Neural Network (NN) models suffer even with a slight shift in input distribution (e.g., scanner type). Fine-tuning a model to transfer knowledge from one domain to another requires a significant amount of labeled data in the target domain. In this paper, we develop an interpretable model that can be efficiently fine-tuned to an unseen target domain with minimal computational cost. We assume the interpretable component of NN to be approximately domain-invariant. However, interpretable models typically underperform compared to their Blackbox (BB) variants. We start with a BB in the source domain and distill it into a mixture of shallow interpretable models using human-understandable concepts. As each interpretable model covers a subset of data, a mixture of interpretable models achieves comparable performance as BB. Further, we use the pseudo-labeling technique from semi-supervised learning (SSL) to learn the concept classifier in the target domain, followed by fine-tuning the interpretable models in the target domain. We evaluate our model using a real-life large-scale chest-X-ray (CXR) classification dataset. The code is available at: urlhttps://github.com/batmanlab/MICCAI-2023-Route-interpret-repeat-CXRs.