Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised Learning via Compact Latent Space Clustering
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 |
|---|---|---|---|
| Apply CCLP regularization rather than standard supervision alone | CNN · SVHN, all labels | error rate: 4.26 \pm 0.10 -> 3.04 \pm 0.05 | Helped |
| Apply CCLP regularization rather than standard supervision alone | CNN · CIFAR10, all labels | error rate: 9.33 \pm 0.14 -> 8.04 \pm 0.18 | No clear effect |
| Apply CCLP regularization rather than standard supervision alone | CNN · MNIST, all labels | error rate: 0.46 \pm 0.03 -> 0.32 \pm 0.03 | No clear effect |
| Use 3–6 Markov-chain steps instead of one step (ablation) | CCLP · MNIST, SVHN, and CIFAR10 validation settings | error rate: 5\%-$25\% | Helped |
| Use Markov chains longer than 10 steps (ablation) | CCLP · MNIST, SVHN, and CIFAR10 validation settings | error rate | Hurt |
| Use multi-step chains to respect existing clusters instead of only one-step transitions (ablation) | CCLP · Two Moons synthetic experiment | cluster structure | Helped |
Closest papers by meaning
- A Flexible Generative Framework for Graph-based Semi-supervised Learning (NeurIPS 2019 · similarity 0.88)
- Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization (ICLR 2018 · similarity 0.87)
- Unsupervised Clustering using Pseudo-semi-supervised Learning (ICLR 2020 · similarity 0.87)
- Matrix Completion for Graph-Based Deep Semi-Supervised Learning (AAAI 2019 · similarity 0.86)
- Semi-Supervised Classification with Graph Convolutional Networks (ICLR 2017 · similarity 0.86)
- Shoestring: Graph-Based Semi-Supervised Classification With Severely Limited Labeled Data (CVPR 2020 · 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.