相关论文: Discriminative Attribution from Counterfactuals

With the growing pervasiveness of artificial intelligence, the ability to explain the inferences made by machine learning models has become increasingly important. Numerous techniques for model explainability have been proposed, with…

Deep learning models are used in critical applications, in which mistakes can have serious consequences. Therefore, it is crucial to understand how and why models generate predictions. This understanding provides useful information to check…

In this expository article we highlight the relevance of explanations for artificial intelligence, in general, and for the newer developments in {\em explainable AI}, referring to origins and connections of and among different approaches.…

The interpretability of deep neural networks is crucial for understanding model decisions in various applications, including computer vision. AttEXplore++, an advanced framework built upon AttEXplore, enhances attribution by incorporating…

One principal approach for illuminating a black-box neural network is feature attribution, i.e. identifying the importance of input features for the network's prediction. The predictive information of features is recently proposed as a…

Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input by incrementally…

Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures, recent evidence suggests that neural networks encode…

Complex machine learning algorithms are used more and more often in critical tasks involving text data, leading to the development of interpretability methods. Among local methods, two families have emerged: those computing importance…

To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…

We propose a fair machine learning algorithm to model interpretable differences between observed and desired human decision-making, with the latter aimed at reducing disparity in a downstream outcome impacted by the human decision. Prior…

To better understand the output of deep neural networks (DNN), attribution based methods have been an important approach for model interpretability, which assign a score for each input dimension to indicate its importance towards the model…

Existing self-supervised learning methods learn representation by means of pretext tasks which are either (1) discriminating that explicitly specify which features should be separated or (2) aligning that precisely indicate which features…

Predictive uncertainties in classification tasks are often a consequence of model inadequacy or insufficient training data. In popular applications, such as image processing, we are often required to scrutinise these uncertainties by…

Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases. Counterfactual explanations are very effective in providing…

Feature attribution is widely used in interpretable machine learning to explain how influential each measured input feature value is for an output inference. However, measurements can be uncertain, and it is unclear how the awareness of…

Machine learning models that operate on graph-structured data, such as molecular graphs or social networks, often make accurate predictions but offer little insight into why certain predictions are made. Counterfactual explanations address…

Explainable AI (XAI) methods focus on explaining what a neural network has learned - in other words, identifying the features that are the most influential to the prediction. In this paper, we call them "distinguishing features". However,…

The expansion of explainable artificial intelligence as a field of research has generated numerous methods of visualizing and understanding the black box of a machine learning model. Attribution maps are generally used to highlight the…

This paper proposes a joint multi-task learning algorithm to better predict attributes in images using deep convolutional neural networks (CNN). We consider learning binary semantic attributes through a multi-task CNN model, where each CNN…

A multitude of explainability methods and associated fidelity performance metrics have been proposed to help better understand how modern AI systems make decisions. However, much of the current work has remained theoretical -- without much…