Research map / Label-efficient and robust learning / Domain adaptation and generalization
Wasserstein Distance Guided Representation Learning for Domain Adaptation
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 Wasserstein-distance-guided representation learning instead of CORAL | MLP domain adaptation · Amazon reviews (12 adaptation tasks) | average accuracy (%): 82.16 -> 82.43 | Helped |
| Use Wasserstein-distance-guided representation learning instead of MMD | MLP domain adaptation · Office-Caltech (Decaf features, 12 adaptation tasks) | average accuracy (%): 92.03 -> 92.74 | Helped |
| Use Wasserstein-distance-guided representation learning instead of DANN | MLP domain adaptation · Office-Caltech (SURF features, 12 adaptation tasks) | average accuracy (%): 46.57 -> 47.25 | Helped |
| Use Wasserstein-distance-guided representation learning instead of MMD | MLP domain adaptation · Email spam (3 public-to-private inbox tasks) | average accuracy (%): 87.00 -> 89.90 | Helped |
| Use Wasserstein-distance-guided representation learning instead of DANN | MLP domain adaptation · 20 Newsgroups (3 adaptation tasks) | average accuracy (%): 95.47 -> 95.77 | Helped |
Closest papers by meaning
- Domain Adaptation with Invariant Representation Learning: What Transformations to Learn? (NeurIPS 2021 · similarity 0.87)
- Bridging Theory and Algorithm for Domain Adaptation (ICML 2019 · similarity 0.87)
- Learning Wasserstein Embeddings (ICLR 2018 · similarity 0.86)
- Distribution-Informed Neural Networks for Domain Adaptation Regression (NeurIPS 2022 · similarity 0.86)
- LAMDA: Label Matching Deep Domain Adaptation (ICML 2021 · similarity 0.86)
- Representation Subspace Distance for Domain Adaptation Regression (ICML 2021 · 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.