Research map / Label-efficient and robust learning / Self-supervised and contrastive
Linear Separation Capacity of Self-Supervised Representation Learning
Shulei Wang
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 |
|---|---|---|---|
| add data augmentation (AIML) to graph Laplacian manifold learning (ablation) | Manifold representation learning · MNIST (digit < 5 vs >= 5, linear classifier) | misclassification rate | Improved |
| increase labeled sample size for downstream linear classifier from 40% to 100% | AIML and CML representations · MNIST | misclassification rate | No clear effect |
| increase unlabeled sample size for representation learning from 40% to 100% | AIML and CML representations · MNIST | misclassification rate | Improved |
Closest papers by meaning
- Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression (ICLR 2024 · similarity 0.89)
- Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections (NeurIPS 2025 · similarity 0.87)
- Curvature Enhanced Data Augmentation for Regression (ICML 2025 · similarity 0.86)
- Self-supervised Representation Learning from Random Data Projectors (ICLR 2024 · similarity 0.85)
- Cross-Entropy Is All You Need To Invert the Data Generating Process (ICLR 2025 · similarity 0.85)
- An Augmentation-Aware Theory for Self-Supervised Contrastive Learning (ICML 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.
