English

GICDM: Mitigating Hubness for Reliable Distance-Based Generative Model Evaluation

Machine Learning 2026-05-29 v3 Artificial Intelligence Machine Learning

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.

Keywords

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

R2 v1 2026-07-01T10:41:19.207Z