Federated Learning Optimization Comparison Hub

Reference Surfaces

Top Papers

• FedZMG: Efficient Client-Side Optimization in Federated Learning(7.0)

  Develop a federated learning optimizer that enhances performance on edge devices by reducing client-drift efficiently and without communication overhead.

• FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA(4.0)

  FedRot-LoRA optimizes federated LoRA updates with orthogonal transformations to reduce aggregation errors in decentralized model fine-tuning.

• Gradient Compression May Hurt Generalization: A Remedy by Synthetic Data Guided Sharpness Aware Minimization(1.0)

  Improving federated learning generalization using synthetic data for sharpness-aware optimization.