Research map / Label-efficient and robust learning / Domain adaptation and generalization
Margin-aware Adversarial Domain Adaptation with 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 |
|---|---|---|---|
| Use the MADAOT shallow OT-based adversarial alignment (linear classifier, OT divergence) instead of OT-GL/JDOT | domain adaptation on moons · Moons, angles 50-90 degrees | accuracy (%) | Helped |
| Use MADAOT instead of OT baselines on Amazon Reviews | sentiment analysis · Amazon Reviews, 12 tasks | accuracy | Helped |
| Use MADAOT at small angles (10-40 degrees) vs. OT baselines | moons · Moons, angles 10-40 degrees | accuracy | No clear effect |
| Use MADAOT at angles 70 and 90 degrees | moons · Moons, 70-90 degrees | accuracy (%) | Hurt |
Closest papers by meaning
- Bridging Theory and Algorithm for Domain Adaptation (ICML 2019 · similarity 0.91)
- f-Domain Adversarial Learning: Theory and Algorithms (ICML 2021 · similarity 0.89)
- A DIRT-T Approach to Unsupervised Domain Adaptation (ICLR 2018 · similarity 0.89)
- Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers (ICML 2019 · similarity 0.89)
- Adversarial Multiple Source Domain Adaptation (NeurIPS 2018 · similarity 0.88)
- Reusing the Task-Specific Classifier as a Discriminator: Discriminator-Free Adversarial Domain Adaptation (CVPR 2022 · similarity 0.88)
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.