Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Network

TL;DR

Fed-FSNet introduces a fuzzy synthesizing network to generate I.I.D.-like data samples, effectively mitigating Non-I.I.D. issues in federated learning and improving convergence and model performance while preserving privacy.

Contribution

The paper proposes Fed-FSNet, a novel federated learning framework using a fuzzy synthesizing network to address Non-I.I.D. data challenges at the source, enhancing convergence and performance.

Findings

Significantly mitigates Non-I.I.D. issues in FL.

Achieves faster convergence and better accuracy.

Ensures privacy by avoiding local model parameter sharing.

Abstract

Federated learning (FL) has emerged as a promising privacy-preserving distributed machine learning framework recently. It aims at collaboratively learning a shared global model by performing distributed training locally on edge devices and aggregating local models into a global one without centralized raw data sharing in the cloud server. However, due to the large local data heterogeneities (Non-I.I.D. data) across edge devices, the FL may easily obtain a global model that can produce more shifted gradients on local datasets, thereby degrading the model performance or even suffering from the non-convergence during training. In this paper, we propose a novel FL training framework, dubbed Fed-FSNet, using a properly designed Fuzzy Synthesizing Network (FSNet) to mitigate the Non-I.I.D. FL at-the-source. Concretely, we maintain an edge-agnostic hidden model in the cloud server to estimate a less-accurate while direction-aware inversion of the global model. The hidden model can then fuzzily synthesize several mimic I.I.D. data samples (sample features) conditioned on only the global model, which can be shared by edge devices to facilitate the FL training towards faster and better convergence. Moreover, since the synthesizing process involves neither access to the parameters/updates of local models nor analyzing individual local model outputs, our framework can still ensure the privacy of FL. Experimental results on several FL benchmarks demonstrate that our method can significantly mitigate the Non-I.I.D. issue and obtain better performance against other representative methods.