In this section
@inproceedings{Jiang:2026,
author = {Jiang, J and Leofante, F and Rago, A and Toni, F},
publisher = {International Conference on Learning Representations (ICLR)},
title = {Synthesising counterfactual explanations via label-conditional Gaussian mixture variational autoencoders},
year = {2026}
}
TY - CPAPER
AB - Counterfactual explanations (CEs) provide recourse recommendations for individuals affected by algorithmic decisions. A key challenge is generating CEs that are robust against various perturbation types (e.g. input and model perturbations) while simultaneously satisfying other desirable properties. These include plausibility, ensuring CEs reside on the data manifold, and diversity, providing multiple distinct recourse options for single inputs. Existing methods, however, mostly struggle to address these multifaceted requirements in a unified, model-agnostic manner. We address these limitations by proposing a novel generative framework. First, we introduce the Label-conditional Gaussian Mixture Variational Autoencoder (L-GMVAE), a model trained to learn a structured latent space where each class label is represented by a set of Gaussian components withdiverse, prototypical centroids. Building on this, we present LAPACE (LAtent PAth Counterfactual explanations), a model-agnostic algorithm that synthesises entire paths of CE points by interpolating from inputs’ latent representations to those learned latent centroids. This approach inherently ensures robustness to input changes, as all paths for a given target class converge to the same fixed centroids. Furthermore, the generated paths provide a spectrum of recourse options, allowing users to navigate the trade-off between proximity and plausibility while also encouraging robustness against model changes. In addition, user-specified actionability constraints can also be easily incorporated via lightweight gradientoptimisation through the L-GMVAE’s decoder. Comprehensive experiments show that LAPACE is computationally efficient and achieves competitive performance across eight quantitative metrics.
AU - Jiang,J
AU - Leofante,F
AU - Rago,A
AU - Toni,F
PB - International Conference on Learning Representations (ICLR)
PY - 2026///
TI - Synthesising counterfactual explanations via label-conditional Gaussian mixture variational autoencoders
ER -
