This approach is the first to efficiently generate CFs that are realistic, low-cost and feasible, and accommodates both hard feasible constraints, specified by domain knowledge users, and soft feasible constraints, inferred automatically via causal inference from the dataset.
Abstract
Counterfactual (CF) explanations identify changes that alter an input's classification. While existing methods produce realistic and low-cost CFs, they often fail to ensure feasibility, by suggesting non-constructive modifications or incompatible with future changes (e.g., changing an individual's race to secure a job offer). We introduce a refinement of CF explanations that explicitly enforces feasibility. Our approach is the first to efficiently generate CFs that are realistic, low-cost and feasible. We accommodate both hard feasible constraints, specified by domain knowledge users, and soft feasible constraints, inferred automatically via causal inference from the dataset. Our method, Feasible Counterfactual Explanations (FCx), is based on a modified Variational Autoencoder (VAE) optimized with a multi-factor loss function. We measure the cost of a change based on the absolute change in values (proximity) as well as the number of features changed (sparsity) while realism is measured based on the LOF for density estimation, guaranteeing that CFs reside in densely populated regions. Extensive experiments on four public datasets show that our approach matches state-of-the-art performance across multiple metrics while guaranteeing feasibility.
In the field of Explainable AI (XAI), counterfactual (CF) explanations interpret a model's decision by suggesting the changes to the input that would lead to a more favourable outcome. To be useful in practice, such an explanation should change few features and change them as little as possible, properties known as spa...
The Amortized Variational Counterfactual Generator (AVCG), a generalized optimization framework that formulates counterfactual generation as optimization over an arbitrary distribution of plausible predictive hypotheses rather than a single deterministic predictor, is proposed.
J. Duell, Alejandro Jimenez Rodriguez, Mahault Albarracin· 0 citations
This work proposes a framework for computing CXs for inputs with missing values using flow-based generative models and Mixed-Integer Linear Programming (MILP) and demonstrates that this method is able to generate CXs with higher validity, and lower cost than state-of-the-art methods relying on imputation.
Francesco Leofante, D. Neider, Mustafa Yalçiner· 0 citations
Counterfactuals (CFs) are a widely studied approach for explaining machine learning models. They aim to identify a set of minimal and meaningful perturbations in input features required to alter a prediction of a model, thereby offering insights into decision boundaries. For instance, a CF may describe the changes need...
R. Wijethunga, Vinura Galwaduge, A. Sadhu et al.· IEEE Canadian Journal of Ele...· 0 citations
It is argued that robust CFE methods should be evaluated through a common protocol that specifies the model changes, measures their realized behavioral magnitude, and keeps generation performance separate from robustness.
It is found that an organization's choices on measurement models for feature and labels, business requirements, model validation, and the metric of model success have as much or more impact on the generated counterfactuals as the specifics of the generating method.
Mattia Cerrato, Otto Sahlgren, Xenia Heilmann· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026