Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lalletti, Cristiana, Teso, Stefano
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2407.16515
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929432803934208
author Lalletti, Cristiana
Teso, Stefano
author_facet Lalletti, Cristiana
Teso, Stefano
contents Long-running machine learning models face the issue of concept drift (CD), whereby the data distribution changes over time, compromising prediction performance. Updating the model requires detecting drift by monitoring the data and/or the model for unexpected changes. We show that, however, spurious correlations (SCs) can spoil the statistics tracked by detection algorithms. Motivated by this, we introduce ebc-exstream, a novel detector that leverages model explanations to identify potential SCs and human feedback to correct for them. It leverages an entropy-based heuristic to reduce the amount of necessary feedback, cutting annotation costs. Our preliminary experiments on artificially confounded data highlight the promise of ebc-exstream for reducing the impact of SCs on detection.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16515
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Spurious Correlations in Concept Drift: Can Explanatory Interaction Help?
Lalletti, Cristiana
Teso, Stefano
Machine Learning
Long-running machine learning models face the issue of concept drift (CD), whereby the data distribution changes over time, compromising prediction performance. Updating the model requires detecting drift by monitoring the data and/or the model for unexpected changes. We show that, however, spurious correlations (SCs) can spoil the statistics tracked by detection algorithms. Motivated by this, we introduce ebc-exstream, a novel detector that leverages model explanations to identify potential SCs and human feedback to correct for them. It leverages an entropy-based heuristic to reduce the amount of necessary feedback, cutting annotation costs. Our preliminary experiments on artificially confounded data highlight the promise of ebc-exstream for reducing the impact of SCs on detection.
title Spurious Correlations in Concept Drift: Can Explanatory Interaction Help?
topic Machine Learning
url https://arxiv.org/abs/2407.16515