← Back to all news
arXiv Machine Learning By Wonho Bae, Zakaria Aldeneh, Martin Pelikan, Jan "Honza" Silovsky, Tatiana Likhomanenko, Sheikh Shams Azam

A Practical Recipe for Semi-Supervised Federated ASR: Online Pseudo-Labels with Server Update Stabilization

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 14

CW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation under Foundation-Model Teachers

arXiv:2608. 12773v1 Announce Type: cross Abstract: Semi-supervised semantic segmentation has long turned on one question, which pseudo-labels to trust, and a generation of selection rules, dynamic thresholds, per-class curricula, soft confidence weights, answered it for the noisy, under-confident ResNet teachers of their day.

By Ebenezer Tarubinga
computer-visionbenchmarkssafety
More like this →
arXiv Machine Learning
Sep 10

CALM: Class-wise Agreement and Label-gated Disagreement Modulation for Decentralized Federated Learning

CALM introduces a smooth trust gating mechanism for decentralized federated learning, replacing hard filtering of teacher models with class‑wise, sample‑wise, and label‑based weighting. It allows clients with heterogeneous architectures to distill knowledge from peers without a central server or shared data, even under severe non‑IID label skew. Experiments on CIFAR‑10, SVHN, OrganAMNIST, and Google Speech Commands show that CALM consistently outperforms uniform and hard‑filtered distillation and matches or exceeds other heterogeneous‑FL methods.

By Yifan Ying, Qing Tian
efficiency
More like this →