GICDM: Mitigating Hubness for Reliable Distance-Based Generative Model Evaluation
Abstract
Generative model evaluation commonly relies on high-dimensional embedding spaces to compute distances between samples. We show that dataset representations in these spaces are affected by the hubness phenomenon, which distorts nearest-neighbor relationships and biases distance-based metrics. Building on the classical Iterative Contextual Dissimilarity Measure (ICDM), we introduce Generative ICDM (GICDM), a method to correct neighborhood estimation for both real and generated data. We introduce a multi-scale extension to improve empirical behavior. Extensive experiments on synthetic and real benchmarks demonstrate that GICDM resolves hubness-induced failures, restores reliable metric behavior, and improves alignment with human assessment.
Cite
@article{arxiv.2602.16449,
title = {GICDM: Mitigating Hubness for Reliable Distance-Based Generative Model Evaluation},
author = {Nicolas Salvy and Hugues Talbot and Bertrand Thirion},
journal= {arXiv preprint arXiv:2602.16449},
year = {2026}
}
Comments
Forty-third International Conference on Machine Learning, 2026