Personalized Federated Learning for Appliance Recognition via Context-Aware Feature Decoupling
TL;DR
The proposed personalized federated learning framework for appliance recognition in non-intrusive load monitoring (NILM) to address real-world data heterogeneity enables collaborative training without raw data exchange and mitigates the impact of inter-client label distribution skew.
Abstract
This paper proposes a personalized federated learning framework for appliance recognition in non-intrusive load monitoring (NILM) to address real-world data heterogeneity. Each client maintains a personalized model alongside shared global components. To decouple these components, a context-aware conditional policy module adaptively separates global and personalized information via learnable gating. The method enables collaborative training without raw data exchange and mitigates the impact of inter-client label distribution skew. We evaluate the proposed method under four federated settings: independent and identically distributed (IID), Dirichlet non-IID, house-partitioned, and leave-one-house-out. Experiments on three public datasets show strong and stable performance compared with existing federated approaches. Under Dirichlet skew (α=0.1), our method achieves an accuracy of 93.8±0.9% on PLAID, 92.3±1.4% on WHITED, and 96.6±1.5% on COOLL. In the leave-one-house-out setting, it attains 80.3±2.0% on PLAID. These results demonstrate the effectiveness of the proposed method across challenging non-IID scenarios.