An Abstract Interpretation-Based Data Leakage Static Analysis - INRIA - Institut National de Recherche en Informatique et en Automatique Access content directly
Conference Papers Year : 2024

An Abstract Interpretation-Based Data Leakage Static Analysis

Abstract

Data leakage is a well-known problem in machine learning which occurs when the training and testing datasets are not independent. This phenomenon leads to overly optimistic accuracy estimates at training time, followed by a significant drop in performance when models are deployed in the real world. This can be dangerous, notably when models are used for risk prediction in high-stakes applications. In this paper, we propose an abstract interpretation-based static analysis to prove the absence of data leakage. We implemented it in the NBLyzer framework and we demonstrate its performance and precision on 2111 Jupyter notebooks from the Kaggle competition platform.
Fichier principal
Vignette du fichier
tase2024.pdf (446.4 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04556578 , version 1 (23-04-2024)

Licence

Attribution

Identifiers

  • HAL Id : hal-04556578 , version 1

Cite

Filip Drobnjaković, Pavle Subotic, Caterina Urban. An Abstract Interpretation-Based Data Leakage Static Analysis. 18th International Symposium on Theoretical Aspects of Software Engineering, Jul 2024, Guiyang, China. ⟨hal-04556578⟩
15 View
8 Download

Share

Gmail Facebook X LinkedIn More