Heterogeneous federated bidirectional knowledge distillation transfer semi-supervised modulation recognition

Abstract

The large-scale deployment and rapid development of the new generation mobile communication system underpin the widespread application of a massive and diverse range of Internet of things (IoT) devices.However, the distributed application of IoT devices results to significant disparities in private data and substantial heterogeneity in local processing models, which severely limits the aggregation capability of global intelligent model.Therefore, to tackle the challenges of data heterogeneity, model heterogeneity, and insufficient labeling faced by intelligent modulation recognition in cognitive IoT, an algorithm was proposed for heterogeneous federated bidirectional semi-supervised modulation recognition, which incorporated bidirectional knowledge distillation.In the proposed algorithm, a public pseudo dataset was generated by variational autoencoder in the cloud for supporting uplink global knowledge distillation, and adaptively sharing to the local devices for downlink heterogeneous knowledge distillation, while integrating a semi-supervised algorithm within the distillation process.The simulation results indicate that the proposed algorithm outperforms current federated learning algorithms in terms of effectiveness and applicability in the field of communication signal processing.

Keywords

• federated semi-supervised learning;model heterogeneity;variational autoencoder;knowledge distillation