Federated learning (FL) has emerged as a widely adopted paradigm for enabling edge learning with distributed data while ensuring data privacy. However, the traditional FL with deep neural networks trained via backpropagation can hardly meet the low-latency learning requirements in the sixth generation (6G) mobile networks. This challenge mainly arises from the high-dimensional model parameters to be transmitted and the numerous rounds of communication required for convergence due to the inherent randomness of the training process. To address this issue, we adopt the state-of-the-art principle of maximal coding rate reduction to learn linear discriminative features and extend the resultant white-box neural network into FL, yielding the novel framework of Low-Latency Federated Learning (LoLaFL) via forward-only propagation. LoLaFL enables layer-wise transmissions and aggregation with significantly fewer communication rounds, thereby considerably reducing latency. Additionally, we propose two \emph{nonlinear} aggregation schemes for LoLaFL. The first scheme is based on the proof that the optimal NN parameter aggregation in LoLaFL should be harmonic-mean-like. The second scheme further exploits the low-rank structures of the features and transmits the low-rank-approximated covariance matrices of features to achieve additional latency reduction. Theoretic analysis and experiments are conducted to evaluate the performance of LoLaFL. In comparison with traditional FL, the two nonlinear aggregation schemes for LoLaFL can achieve reductions in latency of over 91\% and 98\%, respectively, while maintaining comparable accuracies.

翻译：联邦学习（Federated Learning, FL）已成为一种广泛采用的范式，能够在确保数据隐私的前提下，利用分布式数据进行边缘学习。然而，传统的基于反向传播训练的深度神经网络联邦学习，难以满足第六代（6G）移动网络的低延迟学习要求。这一挑战主要源于需要传输的高维模型参数，以及训练过程固有的随机性所导致的收敛所需的大量通信轮次。为解决此问题，我们采用最先进的极大编码率缩减原理来学习线性判别特征，并将所得的白盒神经网络扩展至联邦学习中，从而通过仅前向传播构建了新颖的低延迟联邦学习（LoLaFL）框架。LoLaFL支持分层传输与聚合，且所需通信轮次显著减少，从而大幅降低了延迟。此外，我们为LoLaFL提出了两种非线性聚合方案。第一种方案基于以下证明：LoLaFL中神经网络参数的最优聚合应类似于调和平均。第二种方案进一步利用特征的低秩结构，传输特征的低秩近似协方差矩阵，以实现额外的延迟降低。我们通过理论分析和实验评估了LoLaFL的性能。与传统联邦学习相比，LoLaFL的两种非线性聚合方案在保持相当精度的同时，分别能实现超过91%和98%的延迟降低。