paper-with-me

홈 › Papers

Federated Semi-Supervised Domain Adaptation via Knowledge Transfer

2022-07-21 · Madhureeta Das, Xianhao Chen, Xiaoyong Yuan, Lan Zhang

Given the rapidly changing machine learning environments and expensive data labeling, semi-supervised domain adaptation (SSDA) is imperative when the labeled data from the source domain is statistically different from the partially labeled data from the target domain. Most prior SSDA research is centrally performed, requiring access to both source and target data. However, data in many fields nowadays is generated by distributed end devices. Due to privacy concerns, the data might be locally stored and cannot be shared, resulting in the ineffectiveness of existing SSDA research. This paper proposes an innovative approach to achieve SSDA over multiple distributed and confidential datasets, named by Federated Semi-Supervised Domain Adaptation (FSSDA). FSSDA integrates SSDA with federated learning based on strategically designed knowledge distillation techniques, whose efficiency is improved by performing source and target training in parallel. Moreover, FSSDA controls the amount of knowledge transferred across domains by properly selecting a key parameter, i.e., the imitation parameter. Further, the proposed FSSDA can be effectively generalized to multi-source domain adaptation scenarios. Extensive experiments are conducted to demonstrate the effectiveness and efficiency of FSSDA design.

📄 PDF Abstract BibTeX arXiv:2207.10727

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationFederated LearningKnowledge DistillationSemi-supervised Domain AdaptationTransfer Learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Closer to Reality: Practical Semi-Supervised Federated Learning for Foundation Model Adaptation

2025-08-22 · Guangyu Sun, Jingtao Li, Weiming Zhuang, Chen Chen 외 arxiv

Foundation models (FMs) exhibit remarkable generalization but require adaptation to downstream tasks, particularly in privacy-sensitive applications. Due to data privacy regulations, cloud-based FMs cannot directly acces…

Federated LearningAutonomous DrivingObject Detection

FedSemiDG: Domain Generalized Federated Semi-supervised Medical Image Segmentation

2025-01-13 · Zhipeng Deng, Zhe Xu, Tsuyoshi Isshiki, Yefeng Zheng

Medical image segmentation is challenging due to the diversity of medical images and the lack of labeled data, which motivates recent developments in federated semi-supervised learning (FSSL) to leverage a large amount o…

Domain GeneralizationImage SegmentationMedical Image SegmentationPseudo Label+2

Federated Adversarial Domain Adaptation

2019-11-05 · ICLR 2020 1 · Xingchao Peng, Zijun Huang, Yizhe Zhu, Kate Saenko

Federated learning improves data privacy and efficiency in machine learning performed over networks of distributed devices, such as mobile phones, IoT and wearable devices, etc. Yet models trained with federated learning…

DisentanglementDomain AdaptationFederated Learningtext-classification+2

Knowledge distillation for semi-supervised domain adaptation

2019-08-16 · Mauricio Orbes-Arteaga, Jorge Cardoso, Lauge Sørensen, Christian Igel 외

In the absence of sufficient data variation (e.g., scanner and protocol variability) in annotated data, deep neural networks (DNNs) tend to overfit during training. As a result, their performance is significantly lower o…

Domain AdaptationKnowledge DistillationSemi-supervised Domain Adaptation

When does the student surpass the teacher? Federated Semi-supervised Learning with Teacher-Student EMA

2023-01-24 · Jessica Zhao, Sayan Ghosh, Akash Bharadwaj, Chih-Yao Ma

Semi-Supervised Learning (SSL) has received extensive attention in the domain of computer vision, leading to development of promising approaches such as FixMatch. In scenarios where training data is decentralized and res…

Federated Learningimage-classificationImage ClassificationPseudo Label