{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/unsupervised-concept-drift-detection-from","title":"Unsupervised Concept Drift Detection from Deep Learning Representations in Real-time","arxiv_id":"2406.17813","date":"2024-06-24","proceeding":null,"authors":["Salvatore Greco","Bartolomeo Vacchetti","Daniele Apiletti","Tania Cerquitelli"],"abstract":"Concept Drift is a phenomenon in which the underlying data distribution and statistical properties of a target domain change over time, leading to a degradation of the model's performance. Consequently, models deployed in production require continuous monitoring through drift detection techniques. Most drift detection methods to date are supervised, i.e., based on ground-truth labels. However, true labels are usually not available in many real-world scenarios. Although recent efforts have been made to develop unsupervised methods, they often lack the required accuracy, have a complexity that makes real-time implementation in production environments difficult, or are unable to effectively characterize drift. To address these challenges, we propose DriftLens, an unsupervised real-time concept drift detection framework. It works on unstructured data by exploiting the distribution distances of deep learning representations. DriftLens can also provide drift characterization by analyzing each label separately. A comprehensive experimental evaluation is presented with multiple deep learning classifiers for text, image, and speech. Results show that (i) DriftLens performs better than previous methods in detecting drift in $11/13$ use cases; (ii) it runs at least 5 times faster; (iii) its detected drift value is very coherent with the amount of drift (correlation $\\geq 0.85$); (iv) it is robust to parameter changes.","url_abs":"https://arxiv.org/abs/2406.17813v1","url_pdf":"https://arxiv.org/pdf/2406.17813v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"unsupervised-concept-drift-detection-from","repo_url":"https://github.com/grecosalvatore/drift-lens","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"drift-detection","task_name":"Drift Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.17813","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}