Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup
This addresses communication bottlenecks and privacy concerns in federated learning systems, particularly for edge devices with asymmetric network capacities, representing an incremental improvement over existing methods.
The paper tackles the problem of communication efficiency and privacy in distributed machine learning under asymmetric uplink-downlink channels by proposing Mix2FLD, a framework combining federated distillation and federated learning with two-way mixup, achieving up to 16.7% higher test accuracy and reducing convergence time by up to 18.8% compared to standard FL.
This letter proposes a novel communication-efficient and privacy-preserving distributed machine learning framework, coined Mix2FLD. To address uplink-downlink capacity asymmetry, local model outputs are uploaded to a server in the uplink as in federated distillation (FD), whereas global model parameters are downloaded in the downlink as in federated learning (FL). This requires a model output-to-parameter conversion at the server, after collecting additional data samples from devices. To preserve privacy while not compromising accuracy, linearly mixed-up local samples are uploaded, and inversely mixed up across different devices at the server. Numerical evaluations show that Mix2FLD achieves up to 16.7% higher test accuracy while reducing convergence time by up to 18.8% under asymmetric uplink-downlink channels compared to FL.