DifCluE：基于扩散自编码器与模态聚类的生成反事实解释
摘要
为同一类别内的不同模式生成多个反事实解释 presents a significant challenge, as these modes are distinct yet converge under the same classification. Diffusion probabilistic models (DPMs) have demonstrated a strong ability to capture the underlying modes of data distributions. In this paper, we harness the power of a Diffusion Autoencoder to generate multiple distinct counterfactual explanations. By clustering in the latent space, we uncover the directions corresponding to the different modes within a class, enabling the generation of diverse and meaningful counterfactuals. We introduce a novel methodology, DifCluE, which consistently identifies these modes and produces more reliable counterfactual explanations. Our experimental results demonstrate that DifCluE outperforms the current state-of-the-art in generating multiple counterfactual explanations, offering a significant advancement in model interpretability.
引用
@article{arxiv.2502.11509,
title = {DifCluE: Generating Counterfactual Explanations with Diffusion Autoencoders and modal clustering},
author = {Suparshva Jain and Amit Sangroya and Lovekesh Vig},
journal= {arXiv preprint arXiv:2502.11509},
year = {2025}
}