Related papers: Counterfactual Explanation Based on Gradual Constr…

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.…

Visual counterfactual explanations are ideal hypothetical images that change the decision-making of the classifier with high confidence toward the desired class while remaining visually plausible and close to the initial image. In this…

Deep learning has enabled realistic face manipulation (i.e., deepfake), which poses significant concerns over the integrity of the media in circulation. Most existing deep learning techniques for deepfake detection can achieve promising…

This study addresses generating counterfactual explanations with multimodal information. Our goal is not only to classify a video into a specific category, but also to provide explanations on why it is not categorized to a specific class…

Machine-learning models, which are known to accurately predict patterns from large datasets, are crucial in decision making. Consequently, counterfactual explanations-methods explaining predictions by introducing input perturbations-have…

Neural networks are prone to learning shortcuts -- they often model simple correlations, ignoring more complex ones that potentially generalize better. Prior works on image classification show that instead of learning a connection to object…

Deep graph learning models have demonstrated remarkable capabilities in processing graph-structured data and have been widely applied across various fields. However, their complex internal architectures and lack of transparency make it…

Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous…

Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data. However, manipulating such representation to perform meaningful and controllable transformations in the…

Counterfactual inference is a powerful tool, capable of solving challenging problems in high-profile sectors. To perform counterfactual inference, one requires knowledge of the underlying causal mechanisms. However, causal mechanisms cannot…

We propose a BlackBox Counterfactual Explainer, designed to explain image classification models for medical applications. Classical approaches (e.g., saliency maps) that assess feature importance do not explain "how" imaging features in…

The accuracy and understandability of bank failure prediction models are crucial. While interpretable models like logistic regression are favored for their explainability, complex models such as random forest, support vector machines, and…

The purported "black box" nature of neural networks is a barrier to adoption in applications where interpretability is essential. Here we present DeepLIFT (Deep Learning Important FeaTures), a method for decomposing the output prediction of…

Counterfactual explanations are gaining prominence within technical, legal, and business circles as a way to explain the decisions of a machine learning model. These explanations share a trait with the long-established "principal reason"…

Clustering algorithms rely on complex optimisation processes that may be difficult to comprehend, especially for individuals who lack technical expertise. While many explainable artificial intelligence techniques exist for supervised…

We present a method for neural network interpretability by combining feature attribution with counterfactual explanations to generate attribution maps that highlight the most discriminative features between pairs of classes. We show that…

We consider counterfactual explanations, the problem of minimally adjusting features in a source input instance so that it is classified as a target class under a given classifier. This has become a topic of recent interest as a way to…

Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data. These biases, such as spurious correlations, arise due to various observed and unobserved confounding variables in the…

Explanation of AI, as well as fairness of algorithms' decisions and the transparency of the decision model, are becoming more and more important. And it is crucial to design effective and human-friendly techniques when opening the black-box…

We propose a novel approach for inferring the individualized causal effects of a treatment (intervention) from observational data. Our approach conceptualizes causal inference as a multitask learning problem; we model a subject's potential…