相关论文: Saliency strikes back: How filtering out high freq…

Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meaningful input features. We argue that a fundamental cause of…

Why do gradient-based explanations struggle with Transformers, and how can we improve them? We identify gradient flow imbalances in Transformers that violate FullGrad-completeness, a critical property for attribution faithfulness that CNNs…

Explainable Artificial Intelligence (XAI) is a rising field in AI. It aims to produce a demonstrative factor of trust, which for human subjects is achieved through communicative means, which Machine Learning (ML) algorithms cannot solely…

With the advent of deep learning, text generation language models have improved dramatically, with text at a similar level as human-written text. This can lead to rampant misinformation because content can now be created cheaply and…

Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision systems are increasingly deployed as proprietary black-box APIs, exposing only…

Explainable Artificial Intelligence (XAI) aims to provide insights into the decision-making process of AI models, allowing users to understand their results beyond their decisions. A significant goal of XAI is to improve the performance of…

Post-hoc explanation methods are widely used to interpret black-box predictions, but their generation is often computationally expensive and their reliability is not guaranteed. We propose epistemic uncertainty as a low-cost proxy for…

The growing complexity of machine learning and deep learning models has led to an increased reliance on opaque "black box" systems, making it difficult to understand the rationale behind predictions. This lack of transparency is…

As machine learning models become increasingly prevalent in time series applications, Explainable Artificial Intelligence (XAI) methods are essential for understanding their predictions. Within XAI, feature attribution methods aim to…

In this work, we explore various topics that fall under the umbrella of Uncertainty in post-hoc Explainable AI (XAI) methods. We in particular focus on the class of additive feature attribution explanation methods. We first describe our…

Machine learning models in safety-critical settings like healthcare are often blackboxes: they contain a large number of parameters which are not transparent to users. Post-hoc explainability methods where a simple, human-interpretable…

We study fairness in Machine Learning (FairML) through the lens of attribute-based explanations generated for machine learning models. Our hypothesis is: Biased Models have Biased Explanations. To establish that, we first translate existing…

The proliferation of complex, black-box AI models has intensified the need for techniques that can explain their decisions. Feature attribution methods have become a popular solution for providing post-hoc explanations, yet the field has…

Feature attributions are post-training analysis methods that assess how various input features of a machine learning model contribute to an output prediction. Their interpretation is straightforward when features act independently, but it…

Predicting default is essential for banks to ensure profitability and financial stability. While modern machine learning methods often outperform traditional regression techniques, their lack of transparency limits their use in regulated…

The study of the attribution of input features to the output of neural network models is an active area of research. While numerous Explainable AI (XAI) techniques have been proposed to interpret these models, the systematic and automated…

To develop a trustworthy AI system, which aim to identify the input regions that most influence the models decisions. The primary task of existing attribution methods lies in efficiently and accurately identifying the relationships among…

Explainable artificial intelligence (XAI) methods shed light on the predictions of machine learning algorithms. Several different approaches exist and have already been applied in climate science. However, usually missing ground truth…

To this day, a variety of approaches for providing local interpretability of black-box machine learning models have been introduced. Unfortunately, all of these methods suffer from one or more of the following deficiencies: They are either…

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…