Adversarial Federated Consensus Learning for Surface Defect Classification Under Data Heterogeneity in IIoT

TL;DR

This paper introduces AFedCL, a personalized federated learning approach with adversarial training and dynamic consensus strategies to improve surface defect classification accuracy in IIoT under data heterogeneity.

Contribution

The paper proposes a novel personalized federated learning method with adversarial training, dynamic consensus, and adaptive feature fusion to address data heterogeneity in industrial defect classification.

Findings

Achieved up to 5.67% accuracy improvement over state-of-the-art methods.

Effectively mitigated data heterogeneity effects in federated learning.

Enhanced global model generalization in surface defect classification.

Abstract

The challenge of data scarcity hinders the application of deep learning in industrial surface defect classification (SDC), as it's difficult to collect and centralize sufficient training data from various entities in Industrial Internet of Things (IIoT) due to privacy concerns. Federated learning (FL) provides a solution by enabling collaborative global model training across clients while maintaining privacy. However, performance may suffer due to data heterogeneity-discrepancies in data distributions among clients. In this paper, we propose a novel personalized FL (PFL) approach, named Adversarial Federated Consensus Learning (AFedCL), for the challenge of data heterogeneity across different clients in SDC. First, we develop a dynamic consensus construction strategy to mitigate the performance degradation caused by data heterogeneity. Through adversarial training, local models from different clients utilize the global model as a bridge to achieve distribution alignment, alleviating the problem of global knowledge forgetting. Complementing this strategy, we propose a consensus-aware aggregation mechanism. It assigns aggregation weights to different clients based on their efficacy in global knowledge learning, thereby enhancing the global model's generalization capabilities. Finally, we design an adaptive feature fusion module to further enhance global knowledge utilization efficiency. Personalized fusion weights are gradually adjusted for each client to optimally balance global and local features. Compared with state-of-the-art FL methods like FedALA, the proposed AFedCL method achieves an accuracy increase of up to 5.67% on three SDC datasets.