Counterfactual Explanations Under Concept Drift
Addresses the overlooked problem of CFE maintenance for evolving data environments, enabling reliable recourse in online machine learning systems.
Counterfactual explanations (CFEs) become invalid under concept drift in data streams. The proposed lightweight update scheme maintains CFE validity and plausibility at lower cost than regeneration, preserving validity over time.
Counterfactual explanations (CFEs) provide actionable recourse, but most methods assume a static framework with fixed data and a trained classifier. This assumption breaks in evolving data environments, such as data streams, where online models are repeatedly updated under concept drift. We identify CFE maintenance in this setting as a previously overlooked problem: explanations that are valid when generated may silently become invalid as the model evolves, including robust CFEs, which are not designed for continuous drift. We propose a lightweight, model-agnostic update scheme that repairs existing CFEs using local sampling to estimate validity and plausibility directions while preserving proximity to the original instance. Experiments on synthetic drifting streams show that initially created CFEs rapidly lose validity, whereas maintained CFEs preserve validity and local plausibility at a lower cost than repeated regeneration.