arXiv Machine Learning
Jul 21
MTSSL: Meta-Thresholding Semi-Supervised Learning
arXiv:2607. 16363v1 Announce Type: cross Abstract: A large body of Semi-supervised Learning~(SSL) algorithms encounter the threshold $\tau$ to select pseudo-labels.
Imbalanced Semi-Supervised Learning via Label Refinement and Threshold Adjustment
arXiv:2407. 05370v3 Announce Type: replace Abstract: Semi-supervised learning (SSL) algorithms often struggle to perform well when trained on imbalanced data.
Related stories
arXiv Machine Learning
Jul 2
SemiScope: Disentangling Classifier Tuning and Joint Optimization in Semi-Supervised Security Classification
arXiv:2607. 00113v1 Announce Type: new Abstract: Background.
arXiv AI
Aug 24
C-Score: Beyond Accuracy for Robustness Assessment in Semi-Supervised Learning under Open-World Unlabeled Contamination
The paper introduces C-Score, a diagnostic framework for evaluating pseudo‑label‑based semi‑supervised learning (SSL) when unlabeled data may contain out‑of‑distribution (OOD) samples. C-Score assesses training behavior across prediction, feature representation, and optimization, using metrics such as PLE, CCI, Sem‑Drift, and Grad‑Align. Experiments on CIFAR‑10 and CIFAR‑100 with various OOD sources show that C‑Score detects hidden degradation that clean accuracy alone fails to reveal, highlighting the need for internal diagnostic signals in SSL robustness assessment.
arXiv AI
Sep 1
Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning
arXiv:2608.30699v1 Announce Type: cross Abstract: Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to...
arXiv Machine Learning
Jun 24
Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective
arXiv:2512. 10244v2 Announce Type: replace-cross Abstract: Semi-supervised few-shot learning (SSFSL) resembles real-world applications such as auto-annotation, as it aims to learn a model from a few labeled and abundant unlabeled task-specific examples to annotate the unlabeled ones.
arXiv AI
Jun 11
CoVar: Confidence-Variance-Guided Pseudo-Label Selection for Semi-Supervised Learning
arXiv:2601. 11670v3 Announce Type: replace-cross Abstract: Pseudo-label selection in semi-supervised learning is commonly driven by maximum-confidence thresholds, yet confidence alone can be unreliable under model overconfidence and class imbalance.
arXiv AI
Sep 15
Follow the Geometry, Not the Model: Cold Start Semi-Supervised Learning
arXiv:2609.14451v1 Announce Type: cross Abstract: Modern semi-supervised learning (SSL) couples pseudo-label generation and classifier training, using the classifier's own confidence to select the ps...
arXiv AI
Jun 2
Avoiding Structural Failure Modes in Tabular Fair SSL: Online Primal-Dual Allocation under Confidence Gating
arXiv:2605. 16446v2 Announce Type: replace-cross Abstract: Semi-supervised learning (SSL) enables prediction with limited labels, but high-stakes tabular applications (medical, credit, recidivism) require statistical fairness guarantees.
arXiv AI
Aug 25
FedCC: Towards Addressing Label Distribution Skews in Distillation-Based Federated Learning
FedCC is a new algorithm for distillation-based federated learning that tackles label distribution skew by allowing clients to mark ambiguous samples as 'unknown' instead of forcing a potentially wrong classification. By adding this extra class and calibrating pseudo-labels on a public dataset, FedCC balances confidence across majority and minority classes. Experiments show that FedCC outperforms existing methods, achieving 67.3% accuracy even when each client has data from only one of ten classes, whereas baselines drop to near-random performance.
arXiv Machine Learning
Sep 25
Classifier-Dependent Benefits of Pseudo-Labeling for Semi-Supervised Android Malware Attribution
The study evaluates pseudo‑labeling for semi‑supervised learning on Android malware attribution using six classifiers. Results show that the benefit of SSL varies strongly by classifier: SVM gains the most, LightGBM improves modestly, and Random Forest can be harmed at low label ratios. The approach particularly helps hard‑to‑classify families and achieves near‑optimal performance with about 800 labeled samples.
arXiv Machine Learning
Jun 25
FedReLa: Imbalanced Federated Learning via Re-Labeling
arXiv:2606. 26037v1 Announce Type: cross Abstract: Federated learning has emerged as the foremost approach for decentralized model training with privacy preservation.
arXiv Machine Learning
Jun 25
Model-agnostic Mitigation Strategies of Data Imbalance for Regression
arXiv:2506. 01486v2 Announce Type: replace Abstract: Data imbalance persists as a pervasive challenge in regression tasks, introducing bias in model performance and undermining predictive reliability.