Incremental Uncertainty-Aware Performance Monitoring With Active Labeling Intervention

MCML Authors

Thomas Decker

→ Group Volker Tresp
 Database Systems, Data Mining and AI

Volker Tresp

Prof. Dr.

Core PI

Database Systems, Data Mining and AI

Abstract

We study the problem of monitoring machine learning models under gradual distribution shifts, where circumstances change slowly over time, often leading to unnoticed yet significant declines in accuracy. To address this, we propose Incremental Uncertainty-aware Performance Monitoring (IUPM), a novel label-free method that estimates performance changes by modeling gradual shifts using optimal transport. In addition, IUPM quantifies the uncertainty in the performance prediction and introduces an active labeling procedure to restore a reliable estimate under a limited labeling budget. Our experiments show that IUPM outperforms existing performance estimation baselines in various gradual shift scenarios and that its uncertainty awareness guides label acquisition more effectively compared to other strategies.

inproceedings KDT+25

---

AISTATS 2025

28th International Conference on Artificial Intelligence and Statistics. Mai Khao, Thailand, May 03-05, 2025.

---

Authors

A. Koebler • T. Decker • I. Thon • V. Tresp • F. Buettner

---

Links

URL

---

In Collaboration

 Siemens AG

---

Research Area

 A3 | Computational Models