FedPIA: Parameter Importance-Based Optimized Federated Learning to Efficiently Process Non-IID Data on Consumer Electronic Devices

Federated learning is a distributed machine learning method for learning consumer data generated by consumer electronic devices. It provides personalized intelligent services for users while maintaining data privacy by sharing models instead of user data. It is challenging for these methods to learn data efficiently and with high quality. The performance and quality of the model in federated learning are affected by differences in data from different devices, which can lead to divergence between local and global models. Therefore, this paper proposes a parameter importance-based optimization federated learning method, FedPIA. First, two key indicators, including the rate of parameter change and the acceleration rate of parameter change, are provided to evaluate the importance of model parameters, which can reflect the divergence of the data from different devices. Then, a regular term is created based on these indicators to construct a new loss function, reducing the divergence between local and global models. Last, this paper efficiently trains a high-quality model on consumer data with this optimization approach. Experiments show that FedPIA is significantly better than FedCL, FedAvg, and Scaffold in accuracy, F1 scores and communication overhead.

I. Introduction

With the rapid evolution of technologies, such as 5G, IoT and AI technologies, consumer electronic devices, including mobile devices, smartphones, and wearables, have developed rapidly [1], [2]. The number of devices has been growing exponentially and might reach 27 billion by 2027 [3]. Moreover, a large amount of private user data is generated with the use of electronic devices. Many intelligent services based on these data [4], [5], such as personalized recommendations, have been developed for various fields, including medicine [6], [7], new energy [8], construction [9], and smart cities [10], [11]. These intelligent services increase the use of intelligence in our daily lives, but it is a challenge to provide better intelligent services while ensuring user data privacy [12], [13], [14], [15].