Saved in:
Bibliographic Details
Main Authors: Jain, Suparshva, Sangroya, Amit, Vig, Lovekesh
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.11509
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916622420148224
author Jain, Suparshva
Sangroya, Amit
Vig, Lovekesh
author_facet Jain, Suparshva
Sangroya, Amit
Vig, Lovekesh
contents Generating multiple counterfactual explanations for different modes within a class 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11509
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DifCluE: Generating Counterfactual Explanations with Diffusion Autoencoders and modal clustering
Jain, Suparshva
Sangroya, Amit
Vig, Lovekesh
Machine Learning
Artificial Intelligence
Generating multiple counterfactual explanations for different modes within a class 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.
title DifCluE: Generating Counterfactual Explanations with Diffusion Autoencoders and modal clustering
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2502.11509