الباحثون

Sifan Yang

المنشورات 2

نسخة أولية وصول مفتوح

Communication-Efficient Agnostic Federated Learning via Faster Convergence and Compression

Haomin Bai, Junyan Sun, Sifan Yang وآخرون · 2026

Agnostic federated learning (AFL) seeks a model that performs reliably across $m$ heterogeneous workers, but communication remains a bottleneck. We improve communication efficiency by reducing the number of synchronization rounds via faster convergence and the communication cost per round via compression. We first prop …

المؤلفون المشاركون