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

Zhao, Jessica; Ghosh, Sayan; Bharadwaj, Akash; Ma, Chih-Yao

doi:10.48550/arxiv.2301.10114

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concurrently, Zhao etal. [8] achieve state-of-the-art results by selectively adopting the teacher model (updated as the moving average of the model under training) for pseudo-labeling according to data distribution. Despite the promise shown by these approaches, their integration into HFL systems is challenging, as most of them focus primarily on achieving state-of-the-art model accuracy but overlooks training efficiency-a key objective of HFL.…”

Section: Introductionmentioning

confidence: 99%

Efficient Hierarchical Federated Learning for Unlabeled Edge Devices

2024

autml

View full text Add to dashboard Cite

Federated Learning (FL) has emerged as a critical technology to train deep learning models across massive decentralized IoT data on-device. While FL preserves data privacy, it encounters challenges like synchronization latency for model aggregation and single-point failures. In response to these issues, Hierarchical Federated Learning (HFL), which employs edge servers near edge devices to reduce synchronization latency and enhance resilience against single-point failures, has been proposed. However, the assumption of labeled edge devices, i.e, labeled data on edge devices, often proves impractical. Recent researches on semi-supervised FL enable model training for unlabeled edge devices, yet integrating these into HFL presents challenges in balancing model accuracy and training efficiency. This paper introduces FLAGS, a novel semi-supervised HFL system with adaptive global aggregation intervals. Building on the HFL system, FLAGS conducts alternate training between labeled cloud data and unlabeled edge devices. Through an adaptive global aggregation intervals control algorithm, FLAGS navigates the balance between model performance and training efficiency. Evaluation on CIFAR-10 demonstrates FLAGS outperforming baselines within designated time budgets.

show abstract

Section: Introductionmentioning

confidence: 99%

Efficient Hierarchical Federated Learning for Unlabeled Edge Devices

2024

autml

View full text Add to dashboard Cite

show abstract

Personalized Federated Mutual Learning for Unsupervised Camera-aware Person Re-identification

Liu,

Zhuang,

Liu

et al. 2024

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

Person re-identification (ReID) is essential for enhancing security and tracking in multi-camera surveillance systems. To achieve effective person re-identification (ReID) performance across diverse datasets, the Federated Unsupervised Person Re-identification via Camera-aware Clustering (FedUCA) approach has made strides in utilizing distributed datasets while ensuring data privacy. Nevertheless, its uniform model may not adequately cater to the specific characteristics of each participant’s data, given the diversity in camera perspectives and client-specific data variances, thus obtaining degraded results. To address this issue, we propose an advanced framework, Personalized Federated Dual-Model Learning for Camera-Aware Person Re-Identification (PerFedDual), which introduces knowledge-sharing techniques inherent to mutual learning for FedUCA with the camera-centric clustering process. PerFedDual supports a dual-model training approach that creates a cooperative learning space that improves both the global model and client-specific models by exchanging knowledge both ways. The methodology adopted is precisely adjusted to the distinctive data environment of each client, ensuring the protection of privacy while simultaneously enhancing the accuracy and flexibility of ReID models in diverse camera configurations. The empirical evaluation reveals that PerFedDual outperforms FedUCA and alternative federated learning strategies, highlighting the benefits of our technique that leverage collective intelligence to enhance unsupervised person re-identification.

show abstract

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

Cited by 2 publications

References 0 publications

Efficient Hierarchical Federated Learning for Unlabeled Edge Devices

Efficient Hierarchical Federated Learning for Unlabeled Edge Devices

Personalized Federated Mutual Learning for Unsupervised Camera-aware Person Re-identification

Contact Info

Product

Resources

About