Related papers: Interpreting Interpretations: Organizing Attributi…
While diffusion models excel at image generation, their growing adoption raises critical concerns about copyright issues and model transparency. Existing attribution methods identify training examples influencing an entire image, but fall…
As artificial intelligence is increasingly affecting all parts of society and life, there is growing recognition that human interpretability of machine learning models is important. It is often argued that accuracy or other similar…
It is widely recognized that the predictions of deep neural networks are difficult to parse relative to simpler approaches. However, the development of methods to investigate the mode of operation of such models has advanced rapidly in the…
It is a mystery which input features contribute to a neural network's output. Various explanation (feature attribution) methods are proposed in the literature to shed light on the problem. One peculiar observation is that these explanations…
Identification of input data points relevant for the classifier (i.e. serve as the support vector) has recently spurred the interest of researchers for both interpretability as well as dataset debugging. This paper presents an in-depth…
Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust. Concept-based models aim to address this issue by learning tasks based on a set of human-understandable concepts.…
The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the…
We study the attribution problem [28] for deep networks applied to perception tasks. For vision tasks, attribution techniques attribute the prediction of a network to the pixels of the input image. We propose a new technique called…
One way to interpret neural model predictions is to highlight the most important input features---for example, a heatmap visualization over the words in an input sentence. In existing interpretation methods for NLP, a word's importance is…
Interpretability methods for neural networks are difficult to evaluate because we do not understand the black-box models typically used to test them. This paper proposes a framework in which interpretability methods are evaluated using…
Interpretable deep learning is a fundamental building block towards safer AI, especially when the deployment possibilities of deep learning-based computer-aided medical diagnostic systems are so eminent. However, without a computational…
Many interpretable AI approaches have been proposed to provide plausible explanations for a model's decision-making. However, configuring an explainable model that effectively communicates among computational modules has received less…
Interpretability aims to explain the behavior of deep neural networks. Despite rapid growth, there is mounting concern that much of this work has not translated into practical impact, raising questions about its relevance and utility. This…
Feature attribution explains neural network outputs by identifying relevant input features. The attribution has to be faithful, meaning that the attributed features must mirror the input features that influence the output. One recent trend…
To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary…
Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanations cannot be…
When quantitative models are used to support decision-making on complex and important topics, understanding a model's ``reasoning'' can increase trust in its predictions, expose hidden biases, or reduce vulnerability to adversarial attacks.…
Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and support object-level explanations. While these methods perform well in…
A variety of methods exist to explain image classification models. However, whether they provide any benefit to users over simply comparing various inputs and the model's respective predictions remains unclear. We conducted a user study…
Machine learning transparency calls for interpretable explanations of how inputs relate to predictions. Feature attribution is a way to analyze the impact of features on predictions. Feature interactions are the contextual dependence…