DM-PFL: Hitchhiking Generic Federated Learning for Efficient Shift-Robust Personalization

Zhang, Wenhao; Zhou, Zimu; Wang, Yansheng; Tong, Yongxin

doi:10.1145/3580305.3599311

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Other2

Article1

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

LATTE: Layer Algorithm-aware Training Time Estimation for Heterogeneous Federated Learning

Wang,

Zhou,

2024

Proceedings of the 30th Annual International Conference on Mobile Computing and Networking

View full text Add to dashboard Cite

LATTE: Layer Algorithm-aware Training Time Estimation for Heterogeneous Federated Learning

Wang,

Zhou,

2024

Proceedings of the 30th Annual International Conference on Mobile Computing and Networking

View full text Add to dashboard Cite

CASA: Clustered Federated Learning with Asynchronous Clients

Liu,

Ma,

Zhou

et al. 2024

Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

EchoPFL

Li,

Liu,

Zhou

et al. 2024

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

View full text Add to dashboard Cite

The rise of mobile devices with abundant sensory data and local computing capabilities has driven the trend of federated learning (FL) on these devices. And personalized FL (PFL) emerges to train specific deep models for each mobile device to address data heterogeneity and varying performance preferences. However, mobile training times vary significantly, resulting in either delay (when waiting for slower devices for aggregation) or accuracy decline (when aggregation proceeds without waiting). In response, we propose a shift towards asynchronous PFL, where the server aggregates updates as soon as they are available. Nevertheless, existing asynchronous protocols are unfit for PFL because they are devised for federated training of a single global model. They suffer from slow convergence and decreased accuracy when confronted with severe data heterogeneity prevalent in PFL. Furthermore, they often exclude slower devices for staleness control, which notably compromises accuracy when these devices possess critical personalized data. Therefore, we propose EchoPFL, a coordination mechanism for asynchronous PFL. Central to EchoPFL is to include updates from all mobile devices regardless of their latency. To cope with the inevitable staleness from slow devices, EchoPFL revisits model broadcasting. It intelligently converts the unscalable broadcast to on-demand broadcast, leveraging the asymmetrical bandwidth in wireless networks and the dynamic clustering-based PFL. Experiments show that compared to status quo approaches, EchoPFL achieves a reduction of up to 88.2% in convergence time, an improvement of up to 46% in accuracy, and a decrease of 37% in communication costs.

show abstract

DM-PFL: Hitchhiking Generic Federated Learning for Efficient Shift-Robust Personalization

Cited by 3 publications

References 12 publications

LATTE: Layer Algorithm-aware Training Time Estimation for Heterogeneous Federated Learning

LATTE: Layer Algorithm-aware Training Time Estimation for Heterogeneous Federated Learning

CASA: Clustered Federated Learning with Asynchronous Clients

EchoPFL

Contact Info

Product

Resources

About