Research map / Federated learning and privacy / Personalized and heterogeneous FL
Class Balanced Adaptive Pseudo Labeling for Federated Semi-Supervised Learning
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 |
|---|---|---|---|
| Use fixed pseudo labeling instead of batch-based pseudo labeling | Fed-Consist · SVHN | test accuracy: 70.56 -> 86.57 | Helped |
| Add class balanced adaptive thresholds to fixed pseudo labeling (ablation) | CBAFed · CIFAR-10 | accuracy: 59.16 -> 64.29 | Helped |
| Add tail-class data discovery (ablation) | CBAFed · CIFAR-10 | accuracy: 64.29 -> 65.15 | Helped |
| Add residual weight connection (ablation) | CBAFed · CIFAR-10 | accuracy: 65.15 -> 67.08 | Helped |
| Add class balanced adaptive thresholds to fixed pseudo labeling (ablation) | CBAFed · CIFAR-100 | accuracy: 27.64 -> 29.41 | Helped |
| Add tail-class data discovery (ablation) | CBAFed · CIFAR-100 | accuracy: 29.41 -> 29.86 | Helped |
| Add residual weight connection (ablation) | CBAFed · CIFAR-100 | accuracy: 29.86 -> 30.18 | Helped |
| Add class balanced adaptive thresholds to fixed pseudo labeling (ablation) | CBAFed · Fashion-MNIST | accuracy: 79.99 -> 80.87 | Helped |
| Add tail-class data discovery (ablation) | CBAFed · Fashion-MNIST | accuracy: 80.87 -> 84.37 | Helped |
| Add residual weight connection (ablation) | CBAFed · Fashion-MNIST | accuracy: 84.37 -> 85.49 | Helped |
| Use one local training epoch rather than five with fixed pseudo labels (ablation) | Fixed pseudo labeling in FSSL · SVHN | test accuracy | Mixed |
Closest papers by meaning
- (FL)$^2$: Overcoming Few Labels in Federated Semi-Supervised Learning (NeurIPS 2024 · similarity 0.92)
- Mind the Gap: Confidence Discrepancy Can Guide Federated Semi-Supervised Learning Across Pseudo-Mismatch (CVPR 2025 · similarity 0.91)
- Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators (AAAI 2024 · similarity 0.91)
- Progressive Distribution Matching for Federated Semi-Supervised Learning (AAAI 2025 · similarity 0.90)
- SemiDFL: A Semi-Supervised Paradigm for Decentralized Federated Learning (AAAI 2025 · similarity 0.90)
- BSemiFL: Semi-supervised Federated Learning via a Bayesian Approach (ICML 2025 · similarity 0.89)
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.