English
Related papers

Related papers: Statistically Significant Concept-based Explanatio…

200 papers

We propose a new approach to promote safety in classification tasks with established concepts. Our approach -- called a conceptual safeguard -- acts as a verification layer for models that predict a target outcome by first predicting the…

Machine Learning · Computer Science 2024-11-08 Hailey Joren , Charles Marx , Berk Ustun

Thanks to its fine balance between model flexibility and interpretability, the nonparametric additive model has been widely used, and variable selection for this type of model has been frequently studied. However, none of the existing…

Methodology · Statistics 2022-01-10 Xiaowu Dai , Xiang Lyu , Lexin Li

In many fields of science, we observe a response variable together with a large number of potential explanatory variables, and would like to be able to discover which variables are truly associated with the response. At the same time, we…

Methodology · Statistics 2015-10-15 Rina Foygel Barber , Emmanuel J. Candès

Concept-based Models are neural networks that learn a concept extractor to map inputs to high-level concepts and an inference layer to translate these into predictions. Ensuring these modules produce interpretable concepts and behave…

Machine Learning · Computer Science 2026-01-15 Samuele Bortolotti , Emanuele Marconato , Paolo Morettin , Andrea Passerini , Stefano Teso

Model-free knockoffs is a recently proposed technique for identifying covariates that is likely to have an effect on a response variable. The method is an efficient method to control the false discovery rate in hypothesis tests for separate…

Methodology · Statistics 2019-03-29 Lars Holden , Kristoffer Hellton

Understanding intermediate representations of the concepts learned by deep learning classifiers is indispensable for interpreting general model behaviors. Existing approaches to reveal learned concepts often rely on human supervision, such…

Computer Vision and Pattern Recognition · Computer Science 2024-03-07 Wonjoon Chang , Dahee Kwon , Jaesik Choi

Although sparse autoencoders (SAEs) are crucial for identifying interpretable features in neural networks, it is still challenging to distinguish between real computational patterns and erroneous correlations. We introduce Model-X knockoffs…

Machine Learning · Computer Science 2025-11-18 Tsogt-Ochir Enkhbayar

Concept probing has recently garnered increasing interest as a way to help interpret artificial neural networks, dealing both with their typically large size and their subsymbolic nature, which ultimately renders them unfeasible for direct…

Artificial Intelligence · Computer Science 2025-07-25 Manuel de Sousa Ribeiro , Afonso Leote , João Leite

Explainability of deep convolutional neural networks (DCNNs) is an important research topic that tries to uncover the reasons behind a DCNN model's decisions and improve their understanding and reliability in high-risk environments. In this…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Syed Ali Tariq , Tehseen Zia , Mubeen Ghafoor

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

An important problem in machine learning and statistics is to identify features that causally affect the outcome. This is often impossible to do from purely observational data, and a natural relaxation is to identify features that are…

Machine Learning · Statistics 2019-05-30 Jaime Roquero Gimenez , Amirata Ghorbani , James Zou

The knockoff filter is a recent false discovery rate (FDR) control method for high-dimensional linear models. We point out that knockoff has three key components: ranking algorithm, augmented design, and symmetric statistic, and each…

Statistics Theory · Mathematics 2024-02-14 Zheng Tracy Ke , Jun S. Liu , Yucong Ma

This paper introduces a visual sentiment concept classification method based on deep convolutional neural networks (CNNs). The visual sentiment concepts are adjective noun pairs (ANPs) automatically discovered from the tags of web photos,…

Computer Vision and Pattern Recognition · Computer Science 2014-11-03 Tao Chen , Damian Borth , Trevor Darrell , Shih-Fu Chang

Image captioning is a challenging problem owing to the complexity in understanding the image content and diverse ways of describing it in natural language. Recent advances in deep neural networks have substantially improved the performance…

Computer Vision and Pattern Recognition · Computer Science 2017-04-14 Zhou Ren , Xiaoyu Wang , Ning Zhang , Xutao Lv , Li-Jia Li

Counterfactual explanation methods have recently received significant attention for explaining CNN-based image classifiers due to their ability to provide easily understandable explanations that align more closely with human reasoning.…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Syed Ali Tariq , Tehseen Zia

We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images. We use DFF to gain insight into a deep convolutional neural network's learned features, where we…

Machine Learning · Computer Science 2018-10-09 Edo Collins , Radhakrishna Achanta , Sabine Süsstrunk

Few-shot learning aims at recognizing new instances from classes with limited samples. This challenging task is usually alleviated by performing meta-learning on similar tasks. However, the resulting models are black-boxes. There has been…

Machine Learning · Computer Science 2022-03-01 Mohammad Reza Zarei , Majid Komeili

Human explanations of high-level decisions are often expressed in terms of key concepts the decisions are based on. In this paper, we study such concept-based explainability for Deep Neural Networks (DNNs). First, we define the notion of…

Machine Learning · Computer Science 2022-02-09 Chih-Kuan Yeh , Been Kim , Sercan O. Arik , Chun-Liang Li , Tomas Pfister , Pradeep Ravikumar

Selecting important features that have substantial effects on the response with provable type-I error rate control is a fundamental concern in statistics, with wide-ranging practical applications. Existing knockoff filters, although shown…

Methodology · Statistics 2024-02-29 Jiaqi Gu , Zihuai He

How can we understand classification decisions made by deep neural networks? Many existing explainability methods rely solely on correlations and fail to account for confounding, which may result in potentially misleading explanations. To…

Machine Learning · Computer Science 2020-03-02 Yash Goyal , Amir Feder , Uri Shalit , Been Kim