Research map / Label-efficient and robust learning / Semi-supervised learning
Consistent Semi-Supervised Graph Regularization for High Dimensional Data
Xiaoyi Mai, Romain Couillet
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 |
|---|---|---|---|
| center the similarities in graph regularization instead of Laplacian regularization | semi-supervised graph regularization · SBM Case 1, labelled ratio 1/20 | accuracy: 64.2 -> 70.7 | Improved |
| center the similarities instead of Laplacian regularization | semi-supervised graph regularization · SBM Case 2, labelled ratio 1/20 | accuracy: 68.9 -> 80.7 | Improved |
| center the similarities instead of Laplacian regularization | semi-supervised graph regularization · SBM Case 2, labelled ratio 1/5 | accuracy: 79.0 -> 83.9 | Improved |
| use centered regularization instead of iterated Laplacian | graph SSL · SBM Case 1, labelled ratio 1/5 | accuracy: 76.0 -> 77.6 | Improved |
| use centered regularization instead of eigenvector-based method | graph SSL · SBM Case 2, labelled ratio 1/5 | accuracy: 82.3 -> 83.9 | Improved |
| increase number of unlabelled data (n_u) with Laplacian regularization (ablation) | Laplacian regularization · Gaussian mixture, p=100 | accuracy | Hurt |
| increase number of unlabelled data with centered regularization (ablation) | centered regularization · Gaussian mixture, p=100 | accuracy | Improved |
| add additive noise to MNIST data (ablation) | centered vs Laplacian regularization · Noisy MNIST (7,8,9) | accuracy | Improved |
Closest papers by meaning
- Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning (NeurIPS 2021 · similarity 0.92)
- Large-Scale Graph-Based Semi-Supervised Learning via Tree Laplacian Solver (AAAI 2016 · similarity 0.89)
- A Random Matrix Analysis and Improvement of Semi-Supervised Learning for Large Dimensional Data (JMLR 2018 · similarity 0.88)
- Unknown-Aware Graph Regularization for Robust Semi-supervised Learning from Uncurated Data (AAAI 2024 · similarity 0.86)
- Continuous Partitioning for Graph-Based Semi-Supervised Learning (NeurIPS 2024 · similarity 0.86)
- Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective (NeurIPS 2024 · 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.
