Research map / Label-efficient and robust learning / Recognition and long-tail
Unbalanced CO-optimal Transport
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Relax hard marginal constraints with KL penalties to form UCOOT | COOT · Caltech-Office HDA, average across domain pairs | accuracy: 36.29 (± 10.95) -> 42.94 (± 13.93) | Helped |
| Relax hard marginal constraints with KL penalties to form UCOOT | COOT · CITE-seq balanced, cells | FOSCTTM: 0.0127 -> 0.0062 | Helped |
| Relax mass conservation to permit unmatched features | COOT · CITE-seq, ten antibodies and five matching genes | matching accuracy: 60% -> 100% | Helped |
| Relax mass conservation to permit unmatched features | COOT · CITE-seq, ten antibodies and 50 most variable genes | matching accuracy: 50% -> 70% | Helped |
| Relax mass conservation when cell counts differ | COOT · CITE-seq, unequal cell counts | FOSCTTM: 0.1342 vs 0.0127 in the balanced scenario -> 0.0081 vs 0.0062 in the balanced scenario | Helped |
| Use unbalanced rather than balanced COOT under increasing source class-proportion imbalance | COOT · Heterogeneous domain adaptation under target shift | accuracy | Helped |
| Use unbalanced rather than balanced COOT with noisy feature and sample outliers | COOT · MNIST outlier alignment | accuracy | Helped |
| Retain hard marginal constraints instead of relaxing them | COOT · Contaminated sample-feature spaces | transport cost: COOT >= (1 - alpha_s)(1-alpha_f)Delta_0 | Hurt |
Closest papers by meaning
- CO-Optimal Transport (NeurIPS 2020 · similarity 0.93)
- Making transport more robust and interpretable by moving data through a small number of anchor points (ICML 2021 · similarity 0.91)
- Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation (ICLR 2024 · similarity 0.89)
- A Biconvex Formulation for Stable Transport of Mixture Models with a Unique Solution (NeurIPS 2026 · similarity 0.87)
- Variational Regularized Unbalanced Optimal Transport: Single Network, Least Action (NeurIPS 2025 · similarity 0.87)
- Hierarchical Refinement: Optimal Transport to Infinity and Beyond (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.