Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints

@article{Sattler2020ClusteredFL,
  title={Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints},
  author={F. Sattler and K. M{\"u}ller and W. Samek},
  journal={IEEE transactions on neural networks and learning systems},
  year={2020},
  volume={PP}
}
  • F. Sattler, K. Müller, W. Samek
  • Published 2020
  • Computer Science, Mathematics, Medicine
  • IEEE transactions on neural networks and learning systems
Federated learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit its popularity, it has been observed that FL yields suboptimal results if the local clients' data distributions diverge. To address this issue, we present clustered FL (CFL), a novel federated multitask learning (FMTL) framework, which exploits geometric properties of the FL loss surface to group the client population into clusters… Expand
57 Citations
On the Byzantine Robustness of Clustered Federated Learning
Heterogeneous Data-Aware Federated Learning
Federated learning with hierarchical clustering of local updates to improve training on non-IID data
Multi-Center Federated Learning
Federated Learning with Taskonomy for Non-IID Data
The Communication-Aware Clustered Federated Learning Problem
MLMG: Multi-Local and Multi-Global Model Aggregation for Federated Learning
  • Yang Qin, Masaaki Kondo
  • Computer Science
  • 2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)
  • 2021
LINDT: Tackling Negative Federated Learning with Local Adaptation
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 47 REFERENCES
Robust Federated Learning in a Heterogeneous Environment
Robust and Communication-Efficient Federated Learning From Non-i.i.d. Data
On the Convergence of Federated Optimization in Heterogeneous Networks
Variational Federated Multi-Task Learning
Federated Learning with Non-IID Data
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
...
1
2
3
4
5
...