No $D_{train}$: Model-Agnostic Counterfactual Explanations Using Reinforcement Learning
Abstract: Machine learning (ML) methods have experienced significant growth in the past decade, yet their practical application in high-impact real-world domains has been hindered by their opacity. When ML methods are responsible for making critical decisions, stakeholders often require insights into how to alter these decisions. Counterfactual explanations (CFEs) have emerged as a solution, offering interpretations of opaque ML models and providing a pathway to transition from one decision to another. However, most existing CFE methods require access to the model’s training dataset, few methods can handle multivariate time-series, and none of model-agnostic CFE methods can handle multivariate time-series without training datasets. These limitations can be formidable in many scenarios. In this paper, we present NTD-CFE, a novel reinforcement-learning-based model-agnostic CFE method that generates CFEs when training datasets are unavailable. NTD-CFE is suitable for both static and multivariate time-series datasets with continuous and discrete features. NTD-CFE reduces the CFE search space from a multivariate time-series domain to a lower dimensional space and addresses the problem using RL. Users have the flexibility to specify non-actionable, immutable, and preferred features, as well as causal constraints. We demonstrate the performance of NTD-CFE against four baselines on several datasets and find that, despite not having access to a training dataset, NTD-CFE finds CFEs that make significantly fewer and significantly smaller changes to the input time-series. These properties make CFEs more actionable, as the magnitude of change required to alter an outcome is vastly reduced.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: In response to the reviews, the revised version of the paper cites and compares with CFE methods based on Bayesian optimization, provides a more explicit explanation of how constraints can be applied, discusses how the proposed method operates without a training dataset, and further motivates the use of RL. All changes are highlighted in blue text.
Assigned Action Editor: ~Jing_Jiang6
Submission Number: 3755
Loading