{"ID":2872287,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.09616","arxiv_id":"2509.09616","title":"Explaining Concept Drift through the Evolution of Group Counterfactuals","abstract":"Machine learning models in dynamic environments often suffer from concept drift, where changes in the data distribution degrade performance. While detecting this drift is a well-studied topic, explaining how and why the model's decision-making logic changes still remains a significant challenge. In this paper, we introduce a novel methodology to explain concept drift by analyzing the temporal evolution of group-based counterfactual explanations (GCEs). Our approach tracks shifts in the GCEs' cluster centroids and their associated counterfactual action vectors before and after a drift. These evolving GCEs act as an interpretable proxy, revealing structural changes in the model's decision boundary and its underlying rationale. We operationalize this analysis within a three-layer framework that synergistically combines insights from the data layer (distributional shifts), the model layer (prediction disagreement), and our proposed explanation layer. We show that such holistic view allows for a more comprehensive diagnosis of drift, making it possible to distinguish between different root causes, such as a spatial data shift versus a re-labeling of concepts.","short_abstract":"Machine learning models in dynamic environments often suffer from concept drift, where changes in the data distribution degrade performance. While detecting this drift is a well-studied topic, explaining how and why the model's decision-making logic changes still remains a significant challenge. In this paper, we intro...","url_abs":"https://arxiv.org/abs/2509.09616","url_pdf":"https://arxiv.org/pdf/2509.09616v1","authors":"[\"Ignacy Stępka\",\"Jerzy Stefanowski\"]","published":"2025-09-11T16:58:34Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}