Corpus ID: 232075682

Heterogeneity for the Win: One-Shot Federated Clustering

@article{Dennis2021HeterogeneityFT,
  title={Heterogeneity for the Win: One-Shot Federated Clustering},
  author={D. Dennis and T. Li and Virginia Smith},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.00697}
}
In this work, we explore the unique challenges— and opportunities—of unsupervised federated learning (FL). We develop and analyze a one-shot federated clustering scheme, k-FED, based on the widely-used Lloyd’s method for k-means clustering. In contrast to many supervised problems, we show that the issue of statistical heterogeneity in federated networks can in fact benefit our analysis. We analyse k-FED under a center separation assumption and compare it to the best known requirements of its… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 31 REFERENCES
An Efficient Framework for Clustered Federated Learning
  • 15
  • PDF
Agnostic Federated Learning
  • 176
  • PDF
Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints
  • 49
  • PDF
Robust Federated Learning in a Heterogeneous Environment
  • 45
  • PDF
Federated Multi-Task Learning
  • 432
  • PDF
Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies
  • 8
  • Highly Influential
  • PDF
Advances and Open Problems in Federated Learning
  • 614
  • PDF
Federated Learning: Challenges, Methods, and Future Directions
  • 462
  • PDF
...
1
2
3
4
...