Evaluating Counterfactual Explanation Methods on Incomplete Inputs
2026-04-09 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors studied how well current methods for creating counterfactual explanations in machine learning work when some input data is missing. They tested various recent methods to see if these could still provide meaningful and valid explanations despite incomplete inputs. Their results show that methods designed to be more robust perform better but still have difficulty generating valid counterfactuals when data is missing. This suggests a need for new techniques that specifically handle incomplete input data.
Counterfactual ExplanationsMachine LearningMissing DataRobustnessValidityIncomplete InputsExplainable AIAlgorithm Evaluation
Authors
Francesco Leofante, Daniel Neider, Mustafa Yalçıner
Abstract
Existing algorithms for generating Counterfactual Explanations (CXs) for Machine Learning (ML) typically assume fully specified inputs. However, real-world data often contains missing values, and the impact of these incomplete inputs on the performance of existing CX methods remains unexplored. To address this gap, we systematically evaluate recent CX generation methods on their ability to provide valid and plausible counterfactuals when inputs are incomplete. As part of this investigation, we hypothesize that robust CX generation methods will be better suited to address the challenge of providing valid and plausible counterfactuals when inputs are incomplete. Our findings reveal that while robust CX methods achieve higher validity than non-robust ones, all methods struggle to find valid counterfactuals. These results motivate the need for new CX methods capable of handling incomplete inputs.