相关论文: Concept Learning in the Wild: Towards Algorithmic …

The focus of recent research has shifted from merely improving the metrics based performance of Deep Neural Networks (DNNs) to DNNs which are more interpretable to humans. The field of eXplainable Artificial Intelligence (XAI) has observed…

Recent research on graph neural network (GNN) models successfully applied GNNs to classical graph algorithms and combinatorial optimisation problems. This has numerous benefits, such as allowing applications of algorithms when preconditions…

EXplainable AI (XAI) is an essential topic to improve human understanding of deep neural networks (DNNs) given their black-box internals. For computer vision tasks, mainstream pixel-based XAI methods explain DNN decisions by identifying…

Explainable AI (XAI) is an active research area to interpret a neural network's decision by ensuring transparency and trust in the task-specified learned models. Recently, perturbation-based model analysis has shown better interpretation,…

As an emerging interpretable technique, Generalized Additive Models (GAMs) adopt neural networks to individually learn non-linear functions for each feature, which are then combined through a linear model for final predictions. Although…

Deep neural networks (DNNs) have found their way into many applications with potential impact on the safety, security, and fairness of human-machine-systems. Such require basic understanding and sufficient trust by the users. This motivated…

The interpretability of deep neural networks has attracted increasing attention in recent years, and several methods have been created to interpret the "black box" model. Fundamental limitations remain, however, that impede the pace of…

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…

Explainable AI (XAI) underwent a recent surge in research on concept extraction, focusing on extracting human-interpretable concepts from Deep Neural Networks. An important challenge facing concept extraction approaches is the difficulty of…

The thriving research field of concept-based explainable artificial intelligence (C-XAI) investigates how human-interpretable semantic concepts embed in the latent spaces of deep neural networks (DNNs). Post-hoc approaches therein use a set…

Machine learned potentials are becoming a popular tool to define an effective energy model for complex systems, either incorporating electronic structure effects at the atomistic resolution, or effectively renormalizing part of the…

Explainable artificial intelligence (XAI) aims to develop transparent explanatory approaches for "black-box" deep learning models. However,it remains difficult for existing methods to achieve the trade-off of the three key criteria in…

Beyond improving trust and validating model fairness, xAI practices also have the potential to recover valuable scientific insights in application domains where little to no prior human intuition exists. To that end, we propose a method to…

Motivated by the Gestalt pattern theory, and the Winograd Challenge for language understanding, we design synthetic experiments to investigate a deep learning algorithm's ability to infer simple (at least for human) visual concepts, such as…

This paper introduces a novel XAI approach based on near-misses analysis (NMA). This approach reveals a hierarchy of logical 'concepts' inferred from the latent decision-making process of a Neural Network (NN) without delving into its…

Neural network models are widely used in a variety of domains, often as black-box solutions, since they are not directly interpretable for humans. The field of explainable artificial intelligence aims at developing explanation methods to…

Despite their success in various domains, the growing dependence on GNNs raises a critical concern about the nature of the combinatorial reasoning underlying their predictions, which is often hidden within their black-box architectures.…

In this contribution, we provide a comprehensive evaluation of graph neural networks applied to Boolean satisfiability problems, accompanied by an intuitive explanation of the mechanisms enabling the model to generalize to different…

Graph Neural Networks (GNNs) have become a powerful tool for modeling and analyzing data with graph structures. The wide adoption in numerous applications underscores the value of these models. However, the complexity of these methods often…

In this paper, we review recent approaches for explaining concepts in neural networks. Concepts can act as a natural link between learning and reasoning: once the concepts are identified that a neural learning system uses, one can integrate…