# Model Based Explanations of Concept Drift arXiv: https://arxiv.org/abs/2303.09331 ยท HTML: https://mlsanity.com/paper/2303.09331/ ## Key facts - Cited by 21 papers in the map (data through 14 Oct 2026). - Builds on 15 of its 66 references that are in the map. - First posted on arXiv 16 Mar 2023. ## Builds on (most cited first, 15 of 15) - ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016) - [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018) - [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013) - [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017) - [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018) - [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020) - [Techniques for Interpretable Machine Learning](https://mlsanity.com/paper/1808.00033/) (2018) - [Interpretable Counterfactual Explanations Guided by Prototypes](https://mlsanity.com/paper/1907.02584/) (2019) - [Scikit-Multiflow: A Multi-output Streaming Framework](https://mlsanity.com/paper/1807.04662/) (2018) - [Converting High-Dimensional Regression to High-Dimensional Conditional Density Estimation](https://mlsanity.com/paper/1704.08095/) (2017) - [ConceptExplorer: Visual Analysis of Concept Driftsin Multi-source Time-series Data](https://mlsanity.com/paper/2007.15272/) (2020) - [Incremental Permutation Feature Importance (iPFI): Towards Online Explanations on Data Streams](https://mlsanity.com/paper/2209.01939/) (2022) - [Understanding Concept Drift](https://mlsanity.com/paper/1704.00362/) (2017) - [Suitability of Different Metric Choices for Concept Drift Detection](https://mlsanity.com/paper/2202.09486/) (2022) - [A probability theoretic approach to drifting data in continuous time domains](https://mlsanity.com/paper/1912.01969/) (2019) ## Built on by (most cited first, 21 of 21) - [Unsupervised Concept Drift Detection from Deep Learning Representations in Real-time](https://mlsanity.com/paper/2406.17813/) (2024) - [One or Two Things We know about Concept Drift -- A Survey on Monitoring Evolving Environments](https://mlsanity.com/paper/2310.15826/) (2023) - [Variable Selection in Maximum Mean Discrepancy for Interpretable Distribution Comparison](https://mlsanity.com/paper/2311.01537/) (2023) - [iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios](https://mlsanity.com/paper/2306.07775/) (2023) - [Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms](https://mlsanity.com/paper/2601.20131/) (2026) - [Localizing Anomalies in Critical Infrastructure using Model-Based Drift Explanations](https://mlsanity.com/paper/2310.15830/) (2023) - [Explaining Concept Drift through the Evolution of Group Counterfactuals](https://mlsanity.com/paper/2509.09616/) (2025) - [Dynamic Interpretability for Model Comparison via Decision Rules](https://mlsanity.com/paper/2309.17095/) (2023) - [Concept Drift Visualization of SVM with Shifting Window](https://mlsanity.com/paper/2406.13754/) (2024) - [Adapting Rule Representation With Four-Parameter Beta Distribution for Learning Classifier Systems](https://mlsanity.com/paper/2506.03602/) (2025) - [ELIQ: A Label-Free Framework for Quality Assessment of Evolving AI-Generated Images](https://mlsanity.com/paper/2602.03558/) (2026) - [Spurious Correlations in Concept Drift: Can Explanatory Interaction Help?](https://mlsanity.com/paper/2407.16515/) (2024) - [Unsupervised Assessment of Landscape Shifts Based on Persistent Entropy and Topological Preservation](https://mlsanity.com/paper/2410.04183/) (2024) - [Causal Explanation of Concept Drift -- A Truly Actionable Approach](https://mlsanity.com/paper/2507.23389/) (2025) - [QML-HCS: A Hypercausal Quantum Machine Learning Framework for Non-Stationary Environments](https://mlsanity.com/paper/2511.17624/) (2025) - [Drift Localization using Conformal Predictions](https://mlsanity.com/paper/2602.19790/) (2026) - [Counterfactual Explanations Under Concept Drift](https://mlsanity.com/paper/2605.17651/) (2026) - [Dimension-Calibrated Unexplained Mass: An Interpretable Drift Statistic for Contamination Monitoring in Data Streams](https://mlsanity.com/paper/2607.16811/) (2026) - [Challenges in Evaluating Explanation Methods for Static and Evolving Data](https://mlsanity.com/paper/2608.06351/) (2026) - [Does the Explanation Drift Before the Guarantee? Label-Free Early Warning on Evolving Graphs](https://mlsanity.com/paper/2610.16534/) (2026) - [Learning to Detect Shifts in Unstructured Data Streams via Monitoring-by-Betting](https://mlsanity.com/paper/2610.17399/) (2026) ## Abstract (arXiv) The notion of concept drift refers to the phenomenon that the distribution generating the observed data changes over time. If drift is present, machine learning models can become inaccurate and need adjustment. While there do exist methods to detect concept drift or to adjust models in the presence of observed drift, the question of explaining drift, i.e., describing the potentially complex and high dimensional change of distribution in a human-understandable fashion, has hardly been considered so far. This problem is of importance since it enables an inspection of the most prominent characteristics of how and where drift manifests itself. Hence, it enables human understanding of the change and it increases acceptance of life-long learning models. In this paper, we present a novel technology characterizing concept drift in terms of the characteristic change of spatial features based on various explanation techniques. To do so, we propose a methodology to reduce the explanation of concept drift to an explanation of models that are trained in a suitable way extracting relevant information regarding the drift. This way a large variety of explanation schemes is available. Thus, a suitable method can be selected for the problem of drift explanation at hand. We outline the potential of this approach and demonstrate its usefulness in several examples.