Research map / Label-efficient and robust learning / Noisy labels
DualGraph: A Graph-Based Method for Reasoning About Label Noise
HaiYang Zhang, XiMing Xing, Liang Liu
Check 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 |
|---|---|---|---|
| Use DualGraph instead of PENCIL | CIFAR-10 classifier · CIFAR-10, Symmetry-20% | test accuracy (%): 92.64 ± 0.14 -> 96.7 ± 0.53 | Improved |
| Use DualGraph instead of PENCIL | CIFAR-10 classifier · CIFAR-10, Symmetry-50% | test accuracy (%): 90.36 ± 0.23 -> 92.2 ± 1.82 | Improved |
| Use DualGraph instead of PENCIL | CIFAR-10 classifier · CIFAR-10, Symmetry-80% | test accuracy (%): 76.18 ± 1.33 -> 77.2 ± 2.93 | No clear effect |
| Use DualGraph instead of PENCIL | CIFAR-10 classifier · CIFAR-10, Asymmetry-40% | test accuracy (%): 91.01 ± 0.20 -> 94.1 ± 1.41 | Improved |
| Use DualGraph instead of PENCIL | CIFAR-10 classifier · CIFAR-10, Asymmetry-50% | test accuracy (%): 83.8 -> 92.0 | Improved |
| Use DualGraph instead of Co-teaching+ | CIFAR-100 classifier · CIFAR-100, Symmetry-20% | test accuracy (%): 78.71 ± 0.34 -> 88.71 ± 1.23 | Improved |
| Use DualGraph instead of Co-teaching | CIFAR-100 classifier · CIFAR-100, Symmetry-50% | test accuracy (%): 71.30 ± 0.13 -> 75.80 ± 1.82 | Improved |
| Use DualGraph instead of Joint-optim | CIFAR-100 classifier · CIFAR-100, Symmetry-80% | test accuracy (%): 29.60 ± 0.64 -> 50.23 ± 2.93 | Improved |
| Use DualGraph instead of Self-Learning | Clothing1M classifier · Clothing1M, 1M noisy | accuracy: 74.45 -> 80.84 | Improved |
| Use DualGraph instead of Self-Learning | Clothing1M classifier · Clothing1M, 1M noisy + 25k verify | accuracy: 76.44 -> 83.73 | Improved |
| Use DualGraph instead of Self-Learning | Clothing1M classifier · Clothing1M, 1M noisy + 50k clean | accuracy: 81.16 -> 89.82 | Improved |
| Remove distribution-graph supervision by setting λD to zero (ablation) | DualGraph · Clothing1M | test accuracy | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Co-teaching+ — Co-teaching: Robust training of deep neural networks with extremely noisy labels (NeurIPS 2018) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Noise-Robust Learning from Multiple Unsupervised Sources of Inferred Labels (AAAI 2022 · similarity 0.88)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.87)
- Learning the Latent Causal Structure for Modeling Label Noise (NeurIPS 2024 · similarity 0.86)
- Predicting Label Distribution from Ternary Labels (NeurIPS 2024 · similarity 0.86)
- NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noise (NeurIPS 2024 · similarity 0.86)
- Addressing Multi-Label Learning with Partial Labels: From Sample Selection to Label Selection (AAAI 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.
