Research map / Label-efficient and robust learning / Semi-supervised learning
ARC: Adversarial Robust Cuts for Semi-Supervised and Multi-Label 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 |
|---|---|---|---|
| train with adversarial game (ARC) instead of structured hinge loss (SSVM) | min-cut semi-supervised classifier · Diabetes | test Hamming loss: 0.37 -> 0.31 | Helped |
| train with adversarial game (ARC) instead of SSVM | min-cut semi-supervised classifier · Gisette | test Hamming loss: 0.21 -> 0.16 | Helped |
| train with adversarial game (ARC) instead of SSVM | min-cut semi-supervised classifier · Breast Cancer | test Hamming loss: 0.12 -> 0.10 | Helped |
| use game value instead of hinge loss as training bound | SSVM · Diabetes | test loss bound: 1.22 -> 0.35 | Helped |
| ARC instead of binary relevance / MLKNN / Rank SVM | multi-label classifier · Multi-label average over 9 datasets | test Hamming loss: 0.127 -> 0.113 | Helped |
| ARC instead of binary relevance | multi-label classifier · Bibtex | test Hamming loss: 0.015 -> 0.015 | No clear effect |
| ARC instead of binary relevance | multi-label classifier · Scene | test Hamming loss: 0.139 -> 0.110 | Helped |
Closest papers by meaning
- Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterization (NeurIPS 2022 · similarity 0.87)
- Adversarial Label Learning (AAAI 2019 · similarity 0.86)
- Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement (CVPR 2024 · similarity 0.85)
- Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners (CVPR 2024 · similarity 0.85)
- MaxSup: Overcoming Representation Collapse in Label Smoothing (NeurIPS 2025 · similarity 0.85)
- TRiCo: Triadic Game-Theoretic Co-Training for Robust Semi-Supervised Learning (NeurIPS 2025 · 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.