ULOT amortizes fused unbalanced Gromov-Wasserstein optimization: a cross-attention graph network trained to minimize FUGW loss predicts near-optimal transport plans for new graph pairs at quadratic inference cost.
Unbalanced opti- mal transport through non-negative penalized linear regression
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs
ULOT amortizes fused unbalanced Gromov-Wasserstein optimization: a cross-attention graph network trained to minimize FUGW loss predicts near-optimal transport plans for new graph pairs at quadratic inference cost.