Joonhyuk Kang

Cooperative Learning via Federated Distillation over Fading Channels

2020 · arXiv (Cornell University)

Cooperative training methods for distributed machine learning are typically based on the exchange of local gradients or local model parameters. The latter approach is known as Federated Learning (FL). An alternative solution with reduced communication …

Fast-Convergent Federated Learning via Cyclic Aggregation

2022 · arXiv (Cornell University)

Federated learning (FL) aims at optimizing a shared global model over multiple edge devices without transmitting (private) data to the central server. While it is theoretically well-known that FL yields an optimal model -- centrally …

Sparsification on Different Federated Learning Schemes: Comparative Analysis

2022 · 2022 13th International Conference on Information and Communication Technology Convergence (ICTC)

High communication overhead is a major bottleneck in federated learning (FL). To overcome this issue, sparsification is utilized in various compression frameworks. Generally, local clients upload the updated weights to the server. However, in sparsification, …

Compressed Particle-Based Federated Bayesian Learning and Unlearning

2022 · IEEE Communications Letters

Conventional frequentist federated learning (FL) schemes are known to yield overconfident decisions. Bayesian FL addresses this issue by allowing agents to process and exchange uncertainty information encoded in distributions over the model parameters. However, this …