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.
Decoupled Optimization for Teacher-Student Semi-Supervised Learning via a Pioneer Student
Related stories
arXiv AI
Aug 11
Matching Supervision to the Student's Learning Capacity: A Unified Framework for On-Policy Self-Distillation
arXiv:2608. 08176v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) improves the reasoning abilities of LLMs by internalizing privileged context into model parameters through self-distillation.
arXiv Computer Vision
1d ago
Scalable Patch-Level Self-Supervised Learning
arXiv:2610.10013v1 Announce Type: new Abstract: Self-supervised learning (SSL) at scale produces powerful visual representations. However, most scalable SSL methods rely on ad hoc combinations of mul...
arXiv Machine Learning
Jun 16
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.
arXiv Machine Learning
Sep 23
A Practical Recipe for Semi-Supervised Federated ASR: Online Pseudo-Labels with Server Update Stabilization
The paper presents a practical approach to semi‑supervised federated learning for automatic speech recognition (ASR). It demonstrates that using a per‑client online teacher combined with a stabilizing server‑side anchor—where the server continues training on labeled data between rounds—significantly reduces divergence caused by pseudo‑label errors. The authors provide design guidelines that improve in‑domain performance by an average of 20.8 % and cross‑domain performance by 10.0 % over the best prior method, narrowing the gap to fully‑supervised federated learning.
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 AI
Sep 24
AdaDim: Dimensionality Adaptation for SSL Representational Dynamics
AdaDim introduces a training strategy for self‑supervised learning that adaptively balances dimensionality increase and mutual information reduction. By gradually regularizing the projection head while encouraging feature decorrelation and sample uniformity, AdaDim achieves up to 3% performance gains over standard SSL baselines without relying on costly techniques such as queues or predictor networks. The method demonstrates that optimal SSL models do not simply maximize dimensionality or minimize mutual information, but find a trade‑off between the two.
Hugging Face Trending Papers
2d ago
Scalable Patch-Level Self-Supervised Learning
Self-supervised learning (SSL) at scale produces powerful visual representations. However, most scalable SSL methods rely on ad hoc combinations of multiple objectives and stabilization mechanisms. Ta...
arXiv Machine Learning
Jul 27
The Role of Pseudo-labels in Self-training Linear Classifiers on High-dimensional Gaussian Mixture Data
arXiv:2205. 07739v4 Announce Type: replace-cross Abstract: Self-training (ST) is a simple yet effective semi-supervised learning method.
arXiv Machine Learning
Sep 15
Discovering and Preserving Category Correlation Knowledge via Adaptive Reciprocal Knowledge Distillation
arXiv:2609.13199v1 Announce Type: new Abstract: Knowledge distillation aims to improve the performance of lightweight student models by transferring knowledge from larger and more powerful teacher mo...
Hugging Face Trending Papers
Jun 22
Understanding Knowledge Distillation in Post-Training: When It Helps and When It Fails
Large language models (LLMs) achieve strong performance across many tasks, but their high computational cost limits deployment in resource-constrained environments. Knowledge Distillation (KD) offers a practical solution by transferring knowledge from a teacher model of a larger size to a smaller student model.
arXiv Machine Learning
Aug 18
FedADB: Class Anchor-Driven Dual-Branch Federated Learning for Mitigating Forgetting
arXiv:2608. 15310v1 Announce Type: cross Abstract: Multimodal data collected by heterogeneous devices are used for collaborative training, where federated learning (FL) serves as a key paradigm for effective distributed modeling with data privacy preservation.