English
Related papers

Related papers: Interpretable Generative Models through Post-hoc C…

200 papers

Deep generative models, while revolutionizing fields like image and text generation, largely operate as opaque ``black boxes'', hindering human understanding, control, and alignment. While methods like sparse autoencoders (SAEs) show…

Machine Learning · Computer Science 2026-04-03 Lingjing Kong , Shaoan Xie , Guangyi Chen , Yuewen Sun , Xiangchen Song , Eric P. Xing , Kun Zhang

Interpretability and explainability of neural networks is continuously increasing in importance, especially within safety-critical domains and to provide the social right to explanation. Concept based explanations align well with how humans…

Machine Learning · Computer Science 2023-09-11 Rishabh Jain

There is a growing concern about typically opaque decision-making with high-performance machine learning algorithms. Providing an explanation of the reasoning process in domain-specific terms can be crucial for adoption in risk-sensitive…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Aditya Chattopadhyay , Stewart Slocum , Benjamin D. Haeffele , Rene Vidal , Donald Geman

The recent mass adoption of DNNs, even in safety-critical scenarios, has shifted the focus of the research community towards the creation of inherently intrepretable models. Concept Bottleneck Models (CBMs) constitute a popular approach…

Machine Learning · Computer Science 2023-08-22 Konstantinos P. Panousis , Dino Ienco , Diego Marcos

As AI systems grow more capable, it becomes increasingly important that their decisions remain understandable and aligned with human expectations. A key challenge is the limited interpretability of deep models. Post-hoc methods like GradCAM…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 Mahdi Alehdaghi , Rajarshi Bhattacharya , Pourya Shamsolmoali , Rafael M. O. Cruz , Maguelonne Heritier , Eric Granger

Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust. Post-hoc interpretation methods lack transparency in the feature representations learned by the models. This work…

Computer Vision and Pattern Recognition · Computer Science 2021-05-25 Sandareka Wickramanayake , Wynne Hsu , Mong Li Lee

Concept Bottleneck Models (CBNMs) are deep learning models that provide interpretability by enforcing a bottleneck layer where predictions are based exclusively on human-understandable concepts. However, this constraint also restricts…

Machine Learning · Computer Science 2025-10-17 David Debot , Giuseppe Marra

For machine learning models to be most useful in numerous sociotechnical systems, many have argued that they must be human-interpretable. However, despite increasing interest in interpretability, there remains no firm consensus on how to…

Machine Learning · Computer Science 2021-02-03 Andrew Slavin Ross , Nina Chen , Elisa Zhao Hang , Elena L. Glassman , Finale Doshi-Velez

Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge.…

Artificial Intelligence · Computer Science 2025-12-09 Alexandre Rocchi--Henry , Thomas Fel , Gianni Franchi

Concept-based learning enhances prediction accuracy and interpretability by leveraging high-level, human-understandable concepts. However, existing CBL frameworks do not address survival analysis tasks, which involve predicting event times…

Machine Learning · Computer Science 2025-02-11 Stanislav R. Kirpichenko , Lev V. Utkin , Andrei V. Konstantinov , Natalya M. Verbova

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 from information…

Machine Learning · Computer Science 2024-02-12 Ao Sun , Yuanyuan Yuan , Pingchuan Ma , Shuai Wang

Deep Learning methods are renowned for their performances, yet their lack of interpretability prevents them from high-stakes contexts. Recent model agnostic methods address this problem by providing post-hoc interpretability methods by…

Machine Learning · Computer Science 2021-11-30 Marco Repetto

Goal misalignment, reward sparsity and difficult credit assignment are only a few of the many issues that make it difficult for deep reinforcement learning (RL) agents to learn optimal policies. Unfortunately, the black-box nature of deep…

Machine Learning · Computer Science 2024-10-30 Quentin Delfosse , Sebastian Sztwiertnia , Mark Rothermel , Wolfgang Stammer , Kristian Kersting

Recent research on graph neural network (GNN) models successfully applied GNNs to classical graph algorithms and combinatorial optimisation problems. This has numerous benefits, such as allowing applications of algorithms when preconditions…

Machine Learning · Computer Science 2021-07-16 Dobrik Georgiev , Pietro Barbiero , Dmitry Kazhdan , Petar Veličković , Pietro Liò

Today's deep learning systems deliver high performance based on end-to-end training. While they deliver strong performance, these systems are hard to interpret. To address this issue, we propose Semantic Bottleneck Networks (SBN): deep…

Computer Vision and Pattern Recognition · Computer Science 2019-07-30 Max Losch , Mario Fritz , Bernt Schiele

Current language models are unable to quickly learn new concepts on the fly, often requiring a more involved finetuning process to learn robustly. Prompting in-context is not robust to context distractions, and often fails to confer much…

Computation and Language · Computer Science 2024-10-18 Ryan Teehan , Brenden Lake , Mengye Ren

Concept Bottleneck Models (CBM) map images to human-interpretable concepts before making class predictions. Recent approaches automate CBM construction by prompting Large Language Models (LLMs) to generate text concepts and employing Vision…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Nithish Muthuchamy Selvaraj , Xiaobao Guo , Adams Wai-Kin Kong , Alex Kot

Most existing interpretable methods explain a black-box model in a post-hoc manner, which uses simpler models or data analysis techniques to interpret the predictions after the model is learned. However, they (a) may derive contradictory…

Machine Learning · Computer Science 2020-01-22 Mengzhuo Guo , Qingpeng Zhang , Xiuwu Liao , Daniel Dajun Zeng

Concept-based machine learning methods have increasingly gained importance due to the growing interest in making neural networks interpretable. However, concept annotations are generally challenging to obtain, making it crucial to leverage…

Machine Learning · Computer Science 2024-11-06 Alba Carballo-Castro , Sonia Laguna , Moritz Vandenhirtz , Julia E. Vogt

In human-centric settings like education or healthcare, model accuracy and model explainability are key factors for user adoption. Towards these two goals, intrinsically interpretable deep learning models have gained popularity, focusing on…

Machine Learning · Computer Science 2025-05-29 Vinitra Swamy , Syrielle Montariol , Julian Blackwell , Jibril Frej , Martin Jaggi , Tanja Käser