arXiv:2602. 02890v2 Announce Type: replace Abstract: Model soups are strange and strangely effective combinations of parameters.
arXiv:2607. 23273v1 Announce Type: cross Abstract: Computational nutrition needs precise ingredient data, but current databases are incomplete, inconsistent, and built for human reference rather than automated reasoning.
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:2407. 05370v3 Announce Type: replace Abstract: Semi-supervised learning (SSL) algorithms often struggle to perform well when trained on imbalanced data.
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: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:2607. 00113v1 Announce Type: new Abstract: Background.
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:2605.19462v2 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) assumes that solving pretext tasks on unlabeled data yields representations that transfer effectively across d...
The paper proposes a method that first pre‑trains a feature extractor on the target dataset using in‑domain self‑supervised learning (SSL) without labels, then performs standard supervised training on the same noisy dataset. This two‑stage approach eliminates the need for a clean label subset and consistently improves classification accuracy and label‑error detection across synthetic and real‑world noise, especially as noise rates increase. Experiments show that the method matches or surpasses ImageNet and DinoV2 pre‑training, particularly under high noise conditions.
arXiv:2606. 00514v1 Announce Type: new Abstract: Generative modeling and self-supervised representation learning (SSL) optimize structurally different objectives: generative training rewards distributional fidelity, while SSL rewards semantic coherence.
arXiv:2607. 16363v1 Announce Type: cross Abstract: A large body of Semi-supervised Learning~(SSL) algorithms encounter the threshold $\tau$ to select pseudo-labels.
arXiv:2608.24381v1 Announce Type: new Abstract: Self-supervised learning (SSL) has emerged as a promising approach for tabular data, yet its efficacy under extreme label scarcity and test-time missin...