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

• URL: http://arxiv.org/abs/2608.23458v1
• Date: Mon, 24 Aug 2026 16:28:26 GMT
• Title: Traceable Spectral Inference via Influence Functions: Efficient Data Attribution and Error Proxies for the Ariel Mission
• Abstract summary: Interpretability is critical for machine learning models deployed in scientific space missions such as ESA's Ariel.<n>This work investigates training data attribution through influence functions and introduces three key contributions for operational spectroscopy pipelines.
• Score: 0.6908439820101059
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning [51.87858735871145]
  We introduce Iprox, a framework that derives influence-preserving proxies directly from the target model.<n>Iprox consistently outperforms off-the-shelf proxies and baseline methods.
  arXiv  Detail & Related papers  (2026-02-19T20:57:30Z)
• Better Hessians Matter: Studying the Impact of Curvature Approximations in Influence Functions [5.937280131734114]
  We investigate the effect of Hessian approximation quality on influence-function attributions in a controlled classification setting.<n>Our experiments show that better Hessian approximations consistently yield better influence score quality.<n>We further decompose the approximation steps for recent Hessian approximation methods and evaluate each step's influence on attribution accuracy.
  arXiv  Detail & Related papers  (2025-09-27T18:12:35Z)
• Toward Efficient Influence Function: Dropout as a Compression Tool [9.756810956484772]
  We introduce a novel approach that leverages dropout as a gradient compression mechanism to compute the influence function more efficiently.<n>Our method significantly reduces computational and memory overhead, not only during the influence function but also in gradient compression process.
  arXiv  Detail & Related papers  (2025-09-19T06:20:54Z)
• Revisiting Data Attribution for Influence Functions [13.88866465448849]
  This paper comprehensively reviews the data attribution capability of influence functions in deep learning.<n>We discuss their theoretical foundations, recent algorithmic advances for efficient inverse-Hessian-vector product estimation, and evaluate their effectiveness for data attribution and mislabel detection.
  arXiv  Detail & Related papers  (2025-08-10T11:15:07Z)
• Do-PFN: In-Context Learning for Causal Effect Estimation [75.62771416172109]
  We show that Prior-data fitted networks (PFNs) can be pre-trained on synthetic data to predict outcomes.<n>Our approach allows for the accurate estimation of causal effects without knowledge of the underlying causal graph.
  arXiv  Detail & Related papers  (2025-06-06T12:43:57Z)
• A Versatile Influence Function for Data Attribution with Non-Decomposable Loss [3.1615846013409925]
  We propose a Versatile Influence Function (VIF) that can be straightforwardly applied to machine learning models trained with any non-decomposable loss.<n>VIF represents a significant advancement in data attribution, enabling efficient influence-function-based attribution across a wide range of machine learning paradigms.
  arXiv  Detail & Related papers  (2024-12-02T09:59:01Z)
• Machine Learning for Pre/Post Flight UAV Rotor Defect Detection Using Vibration Analysis [54.550658461477106]
  Unmanned Aerial Vehicles (UAVs) will be critical infrastructural components of future smart cities. In order to operate efficiently, UAV reliability must be ensured by constant monitoring for faults and failures. This paper leverages signal processing and Machine Learning methods to analyze the data of a comprehensive vibrational analysis to determine the presence of rotor blade defects.
  arXiv  Detail & Related papers  (2024-04-24T13:50:27Z)
• Loss Bounds for Approximate Influence-Based Abstraction [81.13024471616417]
  Influence-based abstraction aims to gain leverage by modeling local subproblems together with the 'influence' that the rest of the system exerts on them. This paper investigates the performance of such approaches from a theoretical perspective. We show that neural networks trained with cross entropy are well suited to learn approximate influence representations.
  arXiv  Detail & Related papers  (2020-11-03T15:33:10Z)
• Influence Functions in Deep Learning Are Fragile [52.31375893260445]
  influence functions approximate the effect of samples in test-time predictions. influence estimates are fairly accurate for shallow networks. Hessian regularization is important to get highquality influence estimates.
  arXiv  Detail & Related papers  (2020-06-25T18:25:59Z)
• Mixability of Integral Losses: a Key to Efficient Online Aggregation of Functional and Probabilistic Forecasts [72.32459441619388]
  We adapt basic mixable (and exponentially concave) loss functions to compare functional predictions and prove that these adaptations are also mixable (exp-concave)<n>As an application of our main result, we prove that various loss functions used for probabilistic forecasting are mixable (exp-concave)
  arXiv  Detail & Related papers  (2019-12-15T14:25:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.