On Handling Concept Drift, Calibration and Explainability in Non-Stationary Environments and Resources Limited Contexts

Sara Kebir, Karim Tabia

2024

Abstract

In many real-world applications, we face two important challenges: The shift in data distribution and the concept drift on the one hand, and on the other hand, the constraints of limited computational resources, particularly in the field of IoT and edge AI. Although both challenges have been well studied separately, it is rare to tackle these two challenges together. In this paper, we put ourselves in a context of limited resources and we address the problem of the concept and distribution shift not only to ensure a good level of accuracy over time, but also we study the impact that this could have on two complementary aspects which are the confidence/calibration of the model as well as the explainability of the predictions in this context. We first propose a global framework for this problem based on incremental learning, model calibration and lightweight explainability. In particular, we propose a solution to provide feature attributions in a context of limited resources. Finally, we empirically study the impact of incremental learning on model calibration and the quality of explanations.

Paper Citation

in Harvard Style

Kebir S. and Tabia K. (2024). On Handling Concept Drift, Calibration and Explainability in Non-Stationary Environments and Resources Limited Contexts. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 336-346. DOI: 10.5220/0012382200003636

in Bibtex Style

@conference{icaart24,
author={Sara Kebir and Karim Tabia},
title={On Handling Concept Drift, Calibration and Explainability in Non-Stationary Environments and Resources Limited Contexts},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2024},
pages={336-346},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012382200003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - On Handling Concept Drift, Calibration and Explainability in Non-Stationary Environments and Resources Limited Contexts
SN - 978-989-758-680-4
AU - Kebir S.
AU - Tabia K.
PY - 2024
SP - 336
EP - 346
DO - 10.5220/0012382200003636
PB - SciTePress