mlsanityData to 7 Oct 2026

From Concept Drift to Model Degradation: An Overview on Performance-Aware Drift Detectors

arXiv 2203.11070 ↗First posted 21 Mar 2022cs.LG cs.AIcited by 82

Not on the map. Why?

Abstract (arXiv)

The dynamicity of real-world systems poses a significant challenge to deployed predictive machine learning (ML) models. Changes in the system on which the ML model has been trained may lead to performance degradation during the system's life cycle. Recent advances that study non-stationary environments have mainly focused on identifying and addressing such changes caused by a phenomenon called concept drift. Different terms have been used in the literature to refer to the same type of concept drift and the same term for various types. This lack of unified terminology is set out to create confusion on distinguishing between different concept drift variants. In this paper, we start by grouping concept drift types by their mathematical definitions and survey the different terms used in the literature to build a consolidated taxonomy of the field. We also review and classify performance-based concept drift detection methods proposed in the last decade. These methods utilize the predictive model's performance degradation to signal substantial changes in the systems. The classification is outlined in a hierarchical diagram to provide an orderly navigation between the methods. We present a comprehensive analysis of the main attributes and strategies for tracking and evaluating the model's performance in the predictive system. The paper concludes by discussing open research challenges and possible research directions.

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). Builds on 22 of its 197 references that are in the map. First posted on arXiv 21 Mar 2022.

Builds on

22 of 197 references.

References · 22

  1. 2020Learning under Concept Drift: A Reviewcited by 470
  2. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 364
  3. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  4. 2018Deep Learning: A Critical Appraisalcited by 214
  5. 2019Regularized Learning for Domain Adaptation under Label Shiftscited by 118
  6. 2015Characterizing Concept Driftcited by 93
  7. 2019Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Surveycited by 93
  8. 2021Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNscited by 51
  9. 2019Spiking Neural Networks and Online Learning: An Overview and Perspectivescited by 41
  10. 2017A Systematic Study of Online Class Imbalance Learning with Concept Driftcited by 28
  11. 2015Concept Drift Detection for Streaming Datacited by 18
  12. 2017McDiarmid Drift Detection Methods for Evolving Data Streamscited by 13
10 more
  1. 2017Concept Drift and Anomaly Detection in Graph Streamscited by 12
  2. 2022Adaptive Online Incremental Learning for Evolving Data Streamscited by 11
  3. 2017Reservoir of Diverse Adaptive Learners and Stacking Fast Hoeffding Drift Detection Methods for Evolving Data Streamscited by 10
  4. 2018Positive-Unlabeled Classification under Class Prior Shift and Asymmetric Errorcited by 7
  5. 2017Concept Drift Detection and Adaptation with Hierarchical Hypothesis Testingcited by 6
  6. 2019Recurring Concept Meta-learning for Evolving Data Streamscited by 6
  7. 2018Handling Adversarial Concept Drift in Streaming Datacited by 5
  8. 2021Shift Happens: Adjusting Classifierscited by 3
  9. 2017Concept Drift Learning with Alternating Learnerscited by 1
  10. 2020LUNAR: Cellular Automata for Drifting Data Streamscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 17; 2024: 23; 2025: 18; 2026: 18.

82 papers.

Sort:

By area:

  1. 2023Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospectscited by 22
  2. 2024AI Risk Management Should Incorporate Both Safety and Securitycited by 17
  3. 2024Unsupervised Concept Drift Detection from Deep Learning Representations in Real-timecited by 16
  4. 2022DC-Check: A Data-Centric AI checklist to guide the development of reliable machine learning systemscited by 14
  5. 2024Online Drift Detection with Maximum Concept Discrepancycited by 12
  6. 2022Generalization in Neural Networks: A Broad Surveycited by 11
  7. 2024Sequential Harmful Shift Detection Without Labelscited by 9
  8. 2023DA-LSTM: A Dynamic Drift-Adaptive Learning Framework for Interval Load Forecasting with LSTM Networkscited by 8
  9. 2024Confidence-based Estimators for Predictive Performance in Model Monitoringcited by 8
  10. 2024Towards flexible perception with visual memorycited by 8
  11. 2024An Auditing Test To Detect Behavioral Shift in Language Modelscited by 8
  12. 2024Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environmentscited by 8
38 more
  1. 2022Are Concept Drift Detectors Reliable Alarming Systems? -- A Comparative Studycited by 7
  2. 2023How Object Information Improves Skeleton-based Human Action Recognition in Assembly Taskscited by 6
  3. 2023Efficient Concept Drift Handling for Batch Android Malware Detection Modelscited by 5
  4. 2023DSAP: Analyzing Bias Through Demographic Comparison of Datasetscited by 5
  5. 2025AI-driven Wireless Positioning: Fundamentals, Standards, State-of-the-art, and Challengescited by 5
  6. 2025Deep Hierarchical Learning with Nested Subspace Networks for Large Language Modelscited by 5
  7. 2023An investigation of challenges encountered when specifying training data and runtime monitors for safety critical ML applicationscited by 4
  8. 2026DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderationcited by 4
  9. 2023Test & Evaluation Best Practices for Machine Learning-Enabled Systemscited by 3
  10. 2023Is Your Anomaly Detector Ready for Change? Adapting AIOps Solutions to the Real Worldcited by 3
  11. 2024Towards Trustworthy Machine Learning in Production: An Overview of the Robustness in MLOps Approachcited by 3
  12. 2025IncA-DES: An incremental and adaptive dynamic ensemble selection approach using online K-d tree neighborhood search for data streams with concept driftcited by 3
  13. 2023MLHOps: Machine Learning for Healthcare Operationscited by 2
  14. 20235G Positioning Advancements with AI/MLcited by 2
  15. 2024Open-Source Drift Detection Tools in Action: Insights from Two Use Casescited by 2
  16. 2024Operational range bounding of spectroscopy models with anomaly detectioncited by 2
  17. 2025AutoML for Multi-Class Anomaly Compensation of Sensor Driftcited by 2
  18. 2025Understanding Concept Drift with Deprecated Permissions in Android Malware Detectioncited by 2
  19. 2025Using Kolmogorov-Smirnov Distance for Measuring Distribution Shift in Machine Learningcited by 2
  20. 2026Learning Unbiased Cluster Descriptors for Interpretable Imbalanced Concept Drift Detectioncited by 2
  21. 2022Frouros: A Python library for drift detection in machine learning systemscited by 1
  22. 2022Demo: LE3D: A Privacy-preserving Lightweight Data Drift Detection Frameworkcited by 1
  23. 2023Deep incremental learning models for financial temporal tabular datasets with distribution shiftscited by 1
  24. 2023OPTWIN: Drift identification with optimal sub-windowscited by 1
  25. 2024McUDI: Model-Centric Unsupervised Degradation Indicator for Failure Prediction AIOps Solutionscited by 1
  26. 2024Data Quality Aware Approaches for Addressing Model Drift of Semantic Segmentation Modelscited by 1
  27. 2024A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspectivecited by 1
  28. 2024Fault Detection and Monitoring using a Data-Driven Information-Based Strategy: Method, Theory, and Applicationcited by 1
  29. 2024An Efficient Model Maintenance Approach for MLOpscited by 1
  30. 2024Pulling the Carpet Below the Learner's Feet: Genetic Algorithm To Learn Ensemble Machine Learning Model During Concept Driftcited by 1
  31. 2025Sustainable Machine Learning Retraining: Optimizing Energy Efficiency Without Compromising Accuracycited by 1
  32. 2026The Window Dilemma: Why Concept Drift Detection is Ill-Posedcited by 1
  33. 2026Pioneer Agent: Continual Improvement of Small Language Models in Productioncited by 1
  34. 2022Quality Assurance in MLOps Setting: An Industrial Perspectivecited by 0
  35. 2023Boosting classification reliability of NLP transformer models in the long runcited by 0
  36. 2023A Domain-Region Based Evaluation of ML Performance Robustness to Covariate Shiftcited by 0
  37. 2023Changing Data Sources in the Age of Machine Learning for Official Statisticscited by 0
  38. 2023Balancing Computational Efficiency and Forecast Error in Machine Learning-based Time-Series Forecasting: Insights from Live Experiments on Meteorological Nowcastingcited by 0

50 most cited of 82 All 82 (JSON)