Research map / Image generation / GANs
Predictive Adversarial Learning from Positive and Unlabeled Data
Wenpeng Hu, Ran Le, Bing Liu, Feng Ji, Jinwen Ma, Dongyan Zhao, Rui Yan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| replace the GAN generator with a PU classifier and use PAN's KL-divergence adversarial objective | PU learning · YELP, RT, IMDB, 20News, MNIST, CIFAR10 | accuracy: 83.3 -> 83.6; 59.6 -> 64.1; 74.6 -> 78.8; 78.1 -> 81.0; 95.6 -> 96.4; 89.0 -> 89.7 | Improved |
| replace the GAN generator with a PU classifier and use PAN's KL-divergence adversarial objective | PU learning · YELP | F-score: 83.7 -> 83.5 | Hurt |
| replace the GAN generator with a PU classifier and use PAN's KL-divergence adversarial objective | PU learning · RT, IMDB, 20News, MNIST, CIFAR10 | F-score: 66.6 -> 66.6; 76.2 -> 77.1; 78.5 -> 81.1; 95.6 -> 96.5; 86.6 -> 87.2 | Mixed |
| add term III to PAN (ablation) | PAN · YELP | accuracy: 80.67 -> 83.56 | Improved |
| add term III to PAN (ablation) | PAN · 20News | accuracy: 72.63 -> 81.00 | Improved |
| add term III to PAN (ablation) | PAN · MNIST and CIFAR10 | accuracy: 96.30 -> 96.42; 89.38 -> 89.70 | Improved |
| add term III to PAN (ablation) | PAN · YELP, 20News, MNIST, CIFAR10 | F-score: 81.86 -> 83.45; 73.59 -> 81.06; 96.27 -> 96.51; 86.68 -> 87.22 | Improved |
| set the positive training-data ratio to 1% rather than 10% (ablation) | PAN · MNIST | accuracy: 96.42 -> 90.30 | Hurt |
| set the positive training-data ratio to 1% rather than 10% (ablation) | PAN · CIFAR10 | accuracy: 90.77 -> 86.10 | Hurt |
| use λ=0.01 rather than λ=0.0001 (ablation) | PAN · MNIST | accuracy: 90.30 -> 82.70 | Hurt |
| use λ=0.001 rather than λ=0.0001 (ablation) | PAN · MNIST | accuracy: 88.90 -> 90.30 | No clear effect |
Closest papers by meaning
- On Positive-Unlabeled Classification From Corrupted Data in GANs (TPAMI 2025 · similarity 0.90)
- On Positive-Unlabeled Classification in GAN (CVPR 2020 · similarity 0.90)
- Learning from Positive and Unlabeled Data with Arbitrary Positive Shift (NeurIPS 2020 · similarity 0.88)
- Teaching a GAN What Not to Learn (NeurIPS 2020 · similarity 0.86)
- Learning from positive and unlabeled examples -Finite size sample bounds (NeurIPS 2025 · similarity 0.86)
- Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions (CVPR 2024 · similarity 0.85)
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.
