Dynamic Gradient Aggregation for Federated Domain Adaptation

2021-06-14 · Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur, Sefik Emre Eskimez

In this paper, a new learning algorithm for Federated Learning (FL) is introduced. The proposed scheme is based on a weighted gradient aggregation using two-step optimization to offer a flexible training pipeline. Herein, two different flavors of the aggregation method are presented, leading to an order of magnitude improvement in convergence speed compared to other distributed or FL training algorithms like BMUF and FedAvg. Further, the aggregation algorithm acts as a regularizer of the gradient quality. We investigate the effect of our FL algorithm in supervised and unsupervised Speech Recognition (SR) scenarios. The experimental validation is performed based on three tasks: first, the LibriSpeech task showing a speed-up of 7x and 6% word error rate reduction (WERR) compared to the baseline results. The second task is based on session adaptation providing 20% WERR over a powerful LAS model. Finally, our unsupervised pipeline is applied to the conversational SR task. The proposed FL system outperforms the baseline systems in both convergence speed and overall model performance.

📄 PDF Abstract BibTeX arXiv:2106.07578

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation Federated Learning speech-recognition Speech RecognitionUnsupervised Speech Recognition

Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting

2023-02-10 · Enyi Jiang, Yibo Jacky Zhang, Sanmi Koyejo

Federated Domain Adaptation (FDA) describes the federated learning (FL) setting where source clients and a server work collaboratively to improve the performance of a target client where limited data is available. The do…

Domain Adaptation Federated Learning

Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data

2024-12-18 · Junki Mori, Kosuke Kihara, Taiki Miyagawa, Akinori F. Ebihara 외

Federated learning (FL) commonly assumes that the server or some clients have labeled data, which is often impractical due to annotation costs and privacy concerns. Addressing this problem, we focus on a source-free doma…

Domain Adaptation Federated Learning Semantic Segmentation Source-Free Domain Adaptation

Federated Transfer Learning with Dynamic Gradient Aggregation

2020-08-06 · Dimitrios Dimitriadis, Kenichi Kumatani, Robert Gmyr, Yashesh Gaur 외

In this paper, a Federated Learning (FL) simulation platform is introduced. The target scenario is Acoustic Model training based on this platform. To our knowledge, this is the first attempt to apply FL techniques to Spe…

Federated Learning speech-recognition Speech Recognition Transfer Learning

pFedBBN: A Personalized Federated Test-Time Adaptation with Balanced Batch Normalization for Class-Imbalanced Data

2025-11-22 · Md Akil Raihan Iftee, Syed Md. Ahnaf Hasan, Mir Sazzat Hossain, Rakibul Hasan Rajib 외 arxiv

Test-time adaptation (TTA) in federated learning (FL) is crucial for handling unseen data distributions across clients, particularly when faced with domain shifts and skewed class distributions. Class Imbalance (CI) rema…

Test-time Adaptation Federated Learning

Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuning

2026-07-13 · Jing Liu, Chenxuanyin Zou, Jiayang Ren, Gaoyun Fang 외 arxiv

Federated fine-tuning of Multimodal Large Language Models (MLLMs) across distributed networks enables privacy-sensitive adaptation to evolving data streams, yet a fundamental obstacle prevents robust deployment in dynami…

Continual Learning