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.
By Wonho Bae, Zakaria Aldeneh, Martin Pelikan, Jan "Honza" Silovsky, Tatiana Likhomanenko, Sheikh Shams Azam
arXiv:2607. 03068v1 Announce Type: cross Abstract: Semi-supervised semantic segmentation (SSSS) has long turned on one question, which pseudo-labels to trust, and answered it with ever more careful confidence filtering.
By Ebenezer Tarubinga
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.
By Jinshi Liu, Lei He, Pan Liu
arXiv:2607. 15467v1 Announce Type: new Abstract: Knowledge distillation enables an adversary to replicate a proprietary classifier by querying its prediction interface and training a surrogate on the returned probability vectors.
By Khawaja Abaid Ullah, Mohammad Javad Khojasteh
arXiv:2602. 19778v4 Announce Type: replace-cross Abstract: Automatic Chord Recognition (ACR) is constrained by the scarcity of aligned chord labels, as well-aligned annotations are costly to acquire.
By Nghia Phan, Rong Jin, Gang Liu, Xiao Dong
arXiv:2407. 05370v3 Announce Type: replace Abstract: Semi-supervised learning (SSL) algorithms often struggle to perform well when trained on imbalanced data.
By Zeju Li, Ying-Qiu Zheng, Chen Chen, Saad Jbabdi
arXiv:2609.14943v1 Announce Type: new
Abstract: Pseudo-labeling is a strong paradigm for semi-supervised medical image segmentation, yet its effectiveness is highly sensitive to confidence thresholdi...
By Hongyu Liu, Yinlong Wang, Lusha Li, Hui Meng
arXiv:2607. 18088v1 Announce Type: new Abstract: Standard evaluation of many recognition systems contains distribution shift by construction, since benchmarks place disjoint conditions in the training and test splits.
By Weijia Han, Lisha Qu
arXiv:2608. 12600v1 Announce Type: cross Abstract: A critical challenge in deploying online HD map construction systems to real-world scenarios is the scarcity of labeled training data, which limits model generalization in diverse environments.
By Chikao Tsuchiya, Dhaval Bhanderi, David Ilstrup, Hsinmin Cheng, Christopher Ostafew
The paper investigates how to choose the best quantized model from a family of compressed versions when target labels are scarce or unavailable. It finds that a simple rule based on minimum teacher distortion consistently selects the same eight‑bit, per‑channel, unclipped configuration, though this does not minimize empirical target cross‑entropy. The study also shows that confidence‑based estimators perform poorly in overconfident regimes, while output‑distribution estimators can outperform the teacher in some architectures, and that combining distortion with a supervised term can improve selection. Across 134 candidate families, teacher‑anchored selection reduces mean regret with very few labels, though the benefit diminishes after about 25 labels.
By Alejandro Rodriguez Dominguez, Muhammad Shahzad, Xia Hong
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...
By Itai David, Daphna Weinshall
arXiv:2609.39681v1 Announce Type: new
Abstract: Unsupervised domain adaptation (UDA) reduces the annotation burden in panoptic segmentation by leveraging a cost-effectively labeled source domain (e.g...
By Ivan Martinovi\'c, Josip \v{S}ari\'c, Yuki M. Asano, Sini\v{s}a \v{S}egvi\'c