paper-with-me

Papers

Enhancing CBMs Through Binary Distillation with Applications to Test-Time Intervention

2025-03-09 · Matthew Shen, Aliyah Hsu, Abhineet Agarwal, Bin Yu

Concept bottleneck models~(CBM) aim to improve model interpretability by predicting human level ``concepts" in a bottleneck within a deep learning model architecture. However, how the predicted concepts are used in predicting the target still either remains black-box or is simplified to maintain interpretability at the cost of prediction performance. We propose to use Fast Interpretable Greedy Sum-Trees~(FIGS) to obtain Binary Distillation~(BD). This new method, called FIGS-BD, distills a binary-augmented concept-to-target portion of the CBM into an interpretable tree-based model, while mimicking the competitive prediction performance of the CBM teacher. FIGS-BD can be used in downstream tasks to explain and decompose CBM predictions into interpretable binary-concept-interaction attributions and guide adaptive test-time intervention. Across $4$ datasets, we demonstrate that adaptive test-time intervention identifies key concepts that significantly improve performance for realistic human-in-the-loop settings that allow for limited concept interventions.

📄 PDF Abstract BibTeX arXiv:2503.06730

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Tree-Based Leakage Inspection and Control in Concept Bottleneck Models

2024-10-08 · Angelos Ragkousis, Sonali Parbhoo

As AI models grow larger, the demand for accountability and interpretability has become increasingly critical for understanding their decision-making processes. Concept Bottleneck Models (CBMs) have gained attention for …

Decision Making

Editable Concept Bottleneck Models

2024-05-24 · Lijie Hu, Chenyang Ren, Zhengyu Hu, Hongbin Lin 외

Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a humanunderstandable concept layer. However, most previous studies focused on cases where the d…

Controllable Concept Bottleneck Models

2026-01-01 · Hongbin Lin, Chenyang Ren, Juangui Xu, Zhengyu Hu 외 arxiv

Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a human-understandable concept layer. However, most previous studies focused on static scenarios…

Incremental Learning

Sample-efficient Quantum Born Machine through Coding Rate Reduction

2022-11-14 · Pengyuan Zhai

The quantum circuit Born machine (QCBM) is a quantum physics inspired implicit generative model naturally suitable for learning binary images, with a potential advantage of modeling discrete distributions that are hard t…

Eliminating Information Leakage in Hard Concept Bottleneck Models with Supervised, Hierarchical Concept Learning

2024-02-03 · Ao Sun, Yuanyuan Yuan, Pingchuan Ma, Shuai Wang

Concept Bottleneck Models (CBMs) aim to deliver interpretable and interventionable predictions by bridging features and labels with human-understandable concepts. While recent CBMs show promising potential, they suffer f…