CorDis: A Novel Correlation-Based Disentanglement Measure
Hazal Mogultay Ozcan, Sinan Kalkan, Fatos Tunay Yarman Vural · 2025
Disentangled representation learning aims to decompose images into meaningful independent factors of variation. However, measuring the extent of disentanglement remains a challenge. Available measures, such as β-VAE, MIG, SAP score or Explicitness score rely on classifier assumptions, sampling schemes, or mutual information estimators, introducing biases and dependencies to the model. In this paper, we present a novel correlation-based measure, CorDis, which mitigates these dependencies while preserving robust and interpretable insights into disentanglement. We systematically compare CorDis with existing measures. Experimental results demonstrate that CorDis provides a more principled and assumption-light approach to measuring the amount of disentanglement, contributing to the development of universal and consistent benchmarks.