Transport Novelty Distance (TNovD) couples training and generated crystal embeddings via optimal transport and penalizes both memorized and unrealistic samples with a two-regime cost.
Jakob, Aron Walsh, Karsten Reuter, and Johannes T
1 Pith paper cite this work, alongside 3 external citations. Polarity classification is still indexing.
1
Pith paper citing it
3
external citations · OpenAlex
fields
cond-mat.mtrl-sci 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Transport Novelty Distance: A Distributional Metric for Evaluating Material Generative Models
Transport Novelty Distance (TNovD) couples training and generated crystal embeddings via optimal transport and penalizes both memorized and unrealistic samples with a two-regime cost.