Traceable Spectral Inference via Influence Functions: Efficient Data Attribution and Error Proxies for the Ariel Mission

2026-08-24

AI Summary

本文通过影响函数解决ESA的Ariel任务中机器学习模型的可解释性问题，提出了一种基于预测的影响函数方法，并利用该方法计算误差代理。

Abstract

Interpretability is critical for machine learning models deployed in scientific space missions such as ESA's Ariel, where ground truth is unavailable during operations and physical plausibility must be assessed. While most explainable AI methods focus on feature attribution, this work investigates training data attribution through influence functions and introduces three key contributions for operational spectroscopy pipelines. First, influence is reformulated in terms of prediction rather than loss, enabling label-free deployment. Second, by leveraging the closed-form ridge solution of an Extreme Learning Machine, infinitesimal prediction influence is efficiently computed. Third, an influence-based conservative error proxy is derived by propagating training residuals through the influence sensitivities. Evaluated against simulated spectra, the proposed proxy correlates strongly with scale and shape-based spectral errors. Furthermore, influence functions enable the identification of the most influential samples and the approximation of the most harmful ones. Together, these results suggest that this approach can serve as an operational framework for scientific machine learning.

Problem

• Interpretability
• Training Data Attribution
• Influence Functions
• Spectral Errors
• Scientific Machine Learning

Innovation

• Influence Functions
• Data Attribution
• Error Proxy
• Extreme Learning Machine
• Spectral Inference