Exploiting Correlations in Federated Learning: Opportunities and Practical Limitations

ArXi:2604.14751v1 Announce Type: cross The communication bottleneck in federated learning (FL) has spurred extensive research into techniques to reduce the volume of data exchanged between client devices and the central parameter server. In this paper, we systematically classify gradient and model compression schemes into three categories based on the type of correlations they exploit: structural, temporal, and spatial.