Research map / Label-efficient and robust learning / Domain adaptation and generalization
Dual Adversarial Co-Learning for Multi-Domain Text Classification
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 DACL instead of the strongest listed baseline, MAN-NLL | multi-domain text classification · Amazon review dataset (AVG) | accuracy: 85.66 -> 86.59 | Helped |
| Use DACL instead of the strongest listed baseline, MAN-NLL | multi-domain text classification · FDU-MTL (AVG) | accuracy: 88.4 -> 89.1 | Helped |
| Use DACL instead of the strongest listed baseline, MDAN(S) | multi-source unsupervised domain adaptation · Amazon review dataset (AVG) | accuracy: 82.72 -> 83.71 | Helped |
| Add the domain discriminator and domain-based adversarial learning (ablation) | DACL · Amazon review dataset (AVG) | accuracy: 85.86 -> 86.59 | Helped |
| Add the second classifier and discrepancy-based adversarial learning (ablation) | DACL · Amazon review dataset (AVG) | accuracy: 84.95 -> 86.59 | Helped |
| Increase the separation-regularizer weight α from 0.001 to 0.1 | DACL · Amazon review dataset | average accuracy | Helped |
| Increase α beyond 1 | DACL · Amazon review dataset | average accuracy | Hurt |
| Use a large γ value | DACL · Amazon review dataset | average accuracy | Hurt |
Closest papers by meaning
- Improving Domain-Adapted Sentiment Classification by Deep Adversarial Mutual Learning (AAAI 2020 · similarity 0.88)
- Adversarial Multiple Source Domain Adaptation (NeurIPS 2018 · similarity 0.86)
- Multi-Source Domain Adaptation for Visual Sentiment Classification (AAAI 2020 · similarity 0.86)
- Adversarial Training Methods for Semi-Supervised Text Classification (ICLR 2017 · similarity 0.85)
- Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis (AAAI 2020 · similarity 0.85)
- Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization (CVPR 2025 · similarity 0.83)
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.