相关论文: Explainer Divergence Scores (EDS): Some Post-Hoc E…

Deep learning has revolutionized modern data science. However, how to accurately quantify the uncertainty of predictions from large-scale deep neural networks (DNNs) remains an unresolved issue. To address this issue, we introduce a novel…

Deep learning-based support systems have demonstrated encouraging results in numerous clinical applications involving the processing of time series data. While such systems often are very accurate, they have no inherent mechanism for…

This study proposes Evolutionary Causal Discovery (ECD) for causal discovery that tailors response variables, predictor variables, and corresponding operators to research datasets. Utilizing genetic programming for variable relationship…

Convolutional Neural Networks (CNNs) often exploit spurious correlations in datasets, learning superficially predictive yet causally irrelevant features, leading to poor generalization and fairness issues. Deep Feature Reweighting (DFR) is…

Deep neural networks (DNNs) have exhibited remarkable performance across various tasks, yet their susceptibility to spurious correlations poses a significant challenge for out-of-distribution (OOD) generalization. Spurious correlations…

Non-autonomous differential equations are crucial for modeling systems influenced by external signals, yet fitting these models to data becomes particularly challenging when the signals change abruptly. To address this problem, we propose a…

Constraining deep neural networks (DNNs) to learn individual logic types per node, as performed using the DiffLogic network architecture, opens the door to model-specific explanation techniques that quell the complexity inherent to DNNs.…

Spurious correlations are everywhere. While humans often do not perceive them, neural networks are notorious for learning unwanted associations, also known as biases, instead of the underlying decision rule. As a result, practitioners are…

Long-running machine learning models face the issue of concept drift (CD), whereby the data distribution changes over time, compromising prediction performance. Updating the model requires detecting drift by monitoring the data and/or the…

Explainability of deep convolutional neural networks (DCNNs) is an important research topic that tries to uncover the reasons behind a DCNN model's decisions and improve their understanding and reliability in high-risk environments. In this…

Deep neural networks have demonstrated remarkable performance across various domains, yet their decision-making processes remain opaque. Although many explanation methods are dedicated to bringing the obscurity of DNNs to light, they…

Inference latency and trustworthiness of Deep Neural Networks (DNNs) are the bottlenecks in deploying them in critical applications like sensitive tasks. Early Exit (EE) DNNs overcome the latency issues by allowing samples to exit from…

Explaining deep learning model inferences is a promising venue for scientific understanding, improving safety, uncovering hidden biases, evaluating fairness, and beyond, as argued by many scholars. One of the principal benefits of…

Understanding deep neural network (DNN) behavior requires more than evaluating classification accuracy alone; analyzing errors and their predictability is equally crucial. Current evaluation methodologies lack transparency, particularly in…

Causal approaches to post-hoc explainability for black-box prediction models (e.g., deep neural networks trained on image pixel data) have become increasingly popular. However, existing approaches have two important shortcomings: (i) the…

Saliency post-hoc explainability methods are important tools for understanding increasingly complex NLP models. While these methods can reflect the model's reasoning, they may not align with human intuition, making the explanations not…

Although standard Convolutional Neural Networks (CNNs) can be mathematically reinterpreted as Self-Explainable Models (SEMs), their built-in prototypes do not on their own accurately represent the data. Replacing the final linear layer with…

Label noise in datasets could significantly damage the performance and robustness of deep neural networks (DNNs) trained on these datasets. As the size of modern DNNs grows, there is a growing demand for automated tools for detecting such…

The detection of sexism in online content remains an open problem, as harmful language disproportionately affects women and marginalized groups. While automated systems for sexism detection have been developed, they still face two key…

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the…