相关论文: Explaining a Series of Models by Propagating Shapl…

We propose probabilistic Shapley inference (PSI), a novel probabilistic framework to model and infer sufficient statistics of feature attributions in flexible predictive models, via latent random variables whose mean recovers Shapley…

Changes in input distribution can induce shifts in the average predictions of machine learning models. Such prediction shifts may impact downstream business outcomes (e.g. a bank's loan approval rate), so understanding their causes can be…

Large language models (LLMs) have attracted huge interest in practical applications given their increasingly accurate responses and coherent reasoning abilities. Given their nature as black-boxes using complex reasoning processes on their…

Kernel methods are widely used in machine learning and statistics for their flexibility and expressive power, yet their black-box nature limits adoption in high-stakes applications. Shapley value-based attribution methods such as SHAP, and…

Estimating feature importance is a significant aspect of explaining data-based models. Besides explaining the model itself, an equally relevant question is which features are important in the underlying data generating process. We present a…

Allocating costs, benefits, and emissions fairly among power system participant entities represents a persistent challenge. The Shapley value provides an axiomatically fair solution, yet computational barriers have limited its adoption…

Explainability in AI is crucial for model development, compliance with regulation, and providing operational nuance to predictions. The Shapley framework for explainability attributes a model's predictions to its input features in a…

Machine learning (ML) and Deep Learning (DL) methods are being adopted rapidly, especially in computer network security, such as fraud detection, network anomaly detection, intrusion detection, and much more. However, the lack of…

In Machine Learning, the $\mathsf{SHAP}$-score is a version of the Shapley value that is used to explain the result of a learned model on a specific entity by assigning a score to every feature. While in general computing Shapley values is…

Researchers in explainable artificial intelligence have developed numerous methods for helping users understand the predictions of complex supervised learning models. By contrast, explaining the $\textit{uncertainty}$ of model outputs has…

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

This study proposes DeltaSHAP, a novel explainable artificial intelligence (XAI) algorithm specifically designed for online patient monitoring systems. In clinical environments, discovering the causes driving patient risk evolution is…

Cooperative game theory has become a cornerstone of post-hoc interpretability in machine learning, largely through the use of Shapley values. Yet, despite their widespread adoption, Shapley-based methods often rest on axiomatic…

When applied to Image-to-text models, interpretability methods often provide token-by-token explanations namely, they compute a visual explanation for each token of the generated sequence. Those explanations are expensive to compute and…

Interpretability remains a key difficulty in sentiment analysis with Large Language Models (LLMs), particularly in high-stakes applications where it is crucial to comprehend the rationale behind forecasts. This research addressed this by…

Explainable machine learning methods have been accompanied by substantial development. Despite their success, the existing approaches focus more on the general framework with no prior domain expertise. High-stakes financial sectors have…

Feature selection remains a major challenge in medical prediction, where existing approaches such as LASSO often lack robustness and interpretability. We introduce GRASP, a novel framework that couples Shapley value driven attribution with…

Explaining deep convolutional neural networks has been recently drawing increasing attention since it helps to understand the networks' internal operations and why they make certain decisions. Saliency maps, which emphasize salient regions…

With the widespread use of sophisticated machine learning models in sensitive applications, understanding their decision-making has become an essential task. Models trained on tabular data have witnessed significant progress in explanations…

To reduce the heavy computational burden of reactive power optimization of distribution networks, machine learning models are receiving increasing attention. However, most machine learning models (e.g., neural networks) are usually…