Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discovery

arXiv:2404.10356v1 Announce Type: new
Abstract: Trustworthiness is a major prerequisite for the safe application of opaque deep learning models in high-stakes domains like medicine. Understanding the decision-making process not only contributes to fostering trust but might also reveal previously unknown decision criteria of complex models that could advance the state of medical research. The discovery of decision-relevant concepts from black box models is a particularly challenging task. This study proposes Concept Discovery through Latent Diffusion-based Counterfactual Trajectories (CDCT), a novel …

abstract advance application arxiv concept counterfactual cs.ai cs.lg decision deep learning diffusion diffusion models discovery domains latent diffusion models major making medicine process safe state trust type understanding