摘要：Federated learning aims to collaboratively train a machine learning model with possibly geo-distributed workers, which is inherently communication constrained. To achieve communication efficiency, the conventional federated learning algorithms allow the worker to decrease the communication frequency by training the model locally for multiple times. Conventional federated learning architecture, inherited from the parameter server design, relies on highly centralised topologies and large nodes-to-server bandwidths, and convergence property relies on the stochastic gradient descent training in local, which usually causes the large end-to-end training latency in real-world federated learning scenarios. Thus, in this study, the authors propose the adaptive partial gradient aggregation method, a gradient partial level decentralised federated learning, to tackle this problem. In FedPGA, they propose a partial gradient exchange mechanism that makes full use of node-to-node bandwidth for speeding up the communication time. Besides, an adaptive model updating method further reduces the convergence rate by adaptive increasing the step size of the stable direction of gradient descent. The experimental results on various datasets demonstrate that the training time is reduced up to 14 × compared to baselines without accuracy degrade.
关键词：machine learning model; decentralised federated learning; geo-distributed workers; end-to-end training; adaptive model; node-to-node bandwidth; conventional federated learning algorithms; training time; communication efficiency; communication frequency; nodes-to-server bandwidths; gradient partial level decentralised; real-world federated learning scenarios; partial gradient exchange mechanism; inherently communication; communication time; parameter server design; adaptive partial gradient aggregation method; stochastic gradient descent training
