Towards learning to explain with concept bottleneck models: mitigating information leakage

The caltech-ucsd birds-200-2011 dataset

Catherine Wah, Steve Branson, Peter Welinder, Pietro Perona, and Serge Belongie · 2011

Earlier work this paper cites.

Dropout as a bayesian approximation: Representing model uncertainty in deep learning

Yarin Gal and Zoubin Ghahramani · 2016

Earlier work this paper cites.

Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)

Been Kim, Martin Wattenberg, Justin Gilmer, Carrie J. Cai, James Wexler, Fernanda B. Viégas, and Rory Sayres · 2018

Earlier work this paper cites.

Concept whitening for interpretable image recognition

Zhi Chen, Yijie Bei, and Cynthia Rudin · 2020

Earlier work this paper cites.

Now you see me (cme): Concept-based model extraction

Dmitry Kazhdan, Botty Dimanov, Mateja Jamnik, Pietro Liò, and Adrian Weller · 2020

Cited alongside, same era.

Concept bottleneck models

Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, and Percy Liang · 2020

Cited alongside, same era.

On completeness-aware concept-based explanations in deep neural networks

Chih-Kuan Yeh, Been Kim, Sercan Arik, Chun-Liang Li, Tomas Pfister, and Pradeep Ravikumar · 2020

Cited alongside, same era.

Debiasing concept-based explanations with causal analysis

Mohammad Taha Bahadori and David Heckerman · 2021

Cited alongside, same era.

Promises and pitfalls of black-box concept learning models

Original

Anita Mahinpei, Justin Clark, Isaac Lage, Finale Doshi-Velez, and Weiwei Pan · 2021

Later among the works it cites.

Do concept bottleneck models learn as intended?

Original

Andrei Margeloiu, Matthew Ashman, Umang Bhatt, Yanzhi Chen, Mateja Jamnik, and Adrian Weller · 2021

Later among the works it cites.

Cause and effect: Concept-based explanation of neural networks

Mohammad Nokhbeh Zaeem and Majid Komeili · 2021

Later among the works it cites.