相关论文: On Baselines for Local Feature Attributions

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…

Explainable Artificial Intelligence (XAI) aims to provide transparent insights into machine learning models, yet the reliability of many feature attribution methods remains a critical challenge. Prior research (Haufe et al., 2014; Wilming…

Many novel unsupervised feature selection methods are proposed each year, yet their empirical evaluation is limited to supervised and unsupervised evaluation metrics computed on selected datasets, along with comparisons to existing methods.…

In the field of artificial intelligence, AI models are frequently described as `black boxes' due to the obscurity of their internal mechanisms. It has ignited research interest on model interpretability, especially in attribution methods…

Post-hoc explanations for black box models have been studied extensively in classification and regression settings. However, explanations for models that output similarity between two inputs have received comparatively lesser attention. In…

As the capabilities of large-scale pre-trained models evolve, understanding the determinants of their outputs becomes more important. Feature attribution aims to reveal which parts of the input elements contribute the most to model outputs.…

Deep Neural Networks (DNNs) have demonstrated strong capacity in supporting a wide variety of applications. Shapley value has emerged as a prominent tool to analyze feature importance to help people understand the inference process of deep…

We describe a novel attribution method which is grounded in Sensitivity Analysis and uses Sobol indices. Beyond modeling the individual contributions of image regions, Sobol indices provide an efficient way to capture higher-order…

Deep learning models have gained great popularity in statistical modeling because they lead to very competitive regression models, often outperforming classical statistical models such as generalized linear models. The disadvantage of deep…

The goal of this presentation is to build an efficient non-parametric Bayes classifier in the presence of large numbers of predictors. When analyzing such data, parametric models are often too inflexible while non-parametric procedures tend…

Feature attribution methods explain black-box machine learning (ML) models by assigning importance scores to input features. These methods can be computationally expensive for large ML models. To address this challenge, there has been…

Explaining recommendations enables users to understand whether recommended items are relevant to their needs and has been shown to increase their trust in the system. More generally, if designing explainable machine learning models is key…

Recent advancements in DeepFake generation, along with the proliferation of open-source tools, have significantly lowered the barrier for creating synthetic media. This trend poses a serious threat to the integrity and authenticity of…

Human understandable explanation of deep learning models is essential for various critical and sensitive applications. Unlike image or tabular data where the importance of each input feature (for the classifier's decision) can be directly…

Black-box neural network models are widely used in industry and science, yet are hard to understand and interpret. Recently, the attention mechanism was introduced, offering insights into the inner workings of neural language models. This…

Attribution methods shed light on the explainability of data-driven approaches such as deep learning models by uncovering the most influential features in a to-be-explained decision. While determining feature attributions via gradients…

Although neural networks can achieve very high predictive performance on various different tasks such as image recognition or natural language processing, they are often considered as opaque "black boxes". The difficulty of interpreting the…

Feature attribution aims to explain the reasoning behind a black-box model's prediction by identifying the impact of each feature on the prediction. Recent work has extended feature attribution to interactions between multiple features.…

How can we explain the predictions of a black-box model? In this paper, we use influence functions -- a classic technique from robust statistics -- to trace a model's prediction through the learning algorithm and back to its training data,…

An important step towards explaining deep image classifiers lies in the identification of image regions that contribute to individual class scores in the model's output. However, doing this accurately is a difficult task due to the…