Despite the significant improvements made by deep learning models, their adoption in real-world dynamic applications is still limited. Concept drift is among the open issues preventing the widespread exploitation of deep learning models in real-life settings. The dynamic world changes very quickly, and the collected data drifts accordingly. Prediction models, usually trained on static historical data, should be promptly re-trained in case of new real-time drifted data distributions. Although some drift detection methodologies have been proposed over the years, different issues are still open since state-of-the-art solutions show limited effectiveness and efficiency. This paper proposes DRIFT LENS , a novel real-time unsupervised per-label drift detection methodology based on embedding distribution distances in deep learning models. The preliminary experiments performed on a transformer-based model fine-tuned for topic text classification show promising results in drift detection accuracy, drift characterization, and efficient execution time to support real-time concept drift detection.

DRIFT LENS: Real-time unsupervised Concept Drift detection by evaluating per-label embedding distributions / Greco, Salvatore; Cerquitelli, Tania. - ELETTRONICO. - (2021), pp. 1-9. ((Intervento presentato al convegno 2021 International Conference on Data Mining Workshops (ICDMW) tenutosi a Auckland, New Zealand nel December 7-10, 2021 [10.1109/ICDMW53433.2021.00049].

DRIFT LENS: Real-time unsupervised Concept Drift detection by evaluating per-label embedding distributions

Greco, Salvatore;Cerquitelli, Tania
2021

Abstract

Despite the significant improvements made by deep learning models, their adoption in real-world dynamic applications is still limited. Concept drift is among the open issues preventing the widespread exploitation of deep learning models in real-life settings. The dynamic world changes very quickly, and the collected data drifts accordingly. Prediction models, usually trained on static historical data, should be promptly re-trained in case of new real-time drifted data distributions. Although some drift detection methodologies have been proposed over the years, different issues are still open since state-of-the-art solutions show limited effectiveness and efficiency. This paper proposes DRIFT LENS , a novel real-time unsupervised per-label drift detection methodology based on embedding distribution distances in deep learning models. The preliminary experiments performed on a transformer-based model fine-tuned for topic text classification show promising results in drift detection accuracy, drift characterization, and efficient execution time to support real-time concept drift detection.
978-1-6654-2427-1
File in questo prodotto:
File Dimensione Formato  
Drift_Lens_Real-time_unsupervised_Concept_Drift_detection_by_evaluating_per-label_embedding_distributions.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 2.05 MB
Formato Adobe PDF
2.05 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2927432