Analyzing and Repairing Concept Drift Adaptation in Data Stream Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Analyzing and Repairing Concept Drift Adaptation in Data Stream Classification

Résumé

Data collected over time often exhibit changes in distribution, or concept drift, caused by changes in hidden context relevant to the classification task, e.g. weather conditions. Adaptive learning methods are able to retain performance in changing conditions by explicitly detecting concept drift and changing the classifier used to make predictions. However, in realworld conditions, existing methods often select classifiers which poorly represent current data due to adaptation errors, where change in context is misidentified. We propose the AiRStream system, which uses a novel repair algorithm to identify and correct adaptation errors. We identify errors by periodically testing the performance of inactive classifiers. If an error is identified, a backtracking procedure repairs training done under the misidentified context. AiRStream achieves higher accuracy compared to baseline methods and selects classifiers which better match changes in context. A case study on a real-world air quality inference task shows that AiRStream is able to build a robust model of environmental conditions, allowing the adaptions made to concept drift to be analysed and related to changes in weather.

Dates et versions

hal-04468421 , version 1 (20-02-2024)

Identifiants

Citer

Ben Halstead, Yun Sing Koh, Patricia Riddle, Russel Pears, Mykola Pechenizkiy, et al.. Analyzing and Repairing Concept Drift Adaptation in Data Stream Classification. 8th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2021, Porto, Portugal, October 6-9, 2021, Oct 2021, Porto, Portugal. pp.1--2, ⟨10.1109/DSAA53316.2021.9564191⟩. ⟨hal-04468421⟩
1 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More