Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge Based Framework

Abstract

Internet of Things (IoT) have widely penetrated in different aspects of modern life and many intelligent IoT services and applications are emerging. Recently, federated learning is proposed to train a globally shared model by exploiting a massive amount of user-generated data samples on IoT devices while preventing data leakage. However, the device, statistical and model heterogeneities inherent in the complex IoT environments pose great challenges to traditional federated learning, making it unsuitable to be directly deployed. In this paper, we advocate a personalized federated learning framework in a cloud-edge architecture for intelligent IoT applications. To cope with the heterogeneity issues in IoT environments, we investigate emerging personalized federated learning methods which are able to mitigate the negative effects caused by heterogeneities in different aspects. With the power of edge computing, the requirements for fast-processing capacity and low latency in intelligent IoT applications can also be achieved. We finally provide a case study of IoT based human activity recognition to demonstrate the effectiveness of personalized federated learning for intelligent IoT applications. INDEX TERMS Edge computing, federated learning, internet of things, personalization.

A Classification of the Enabling Techniques for Low Latency and Reliable Communications in 5G and Beyond: AI-Enabled Edge Caching

“…In [24], [37], [39], [41], [87]- [90], it was discussed that FL is a promising technique for future intelligent networks due to its superior performance features and added benefits. Edge caching solutions which are based on FL algorithms can guarantee smart models, reduced content delivery latency, improved content acquisition reliability, and improved energy efficiency, all while ensuring preservation of personal data privacy and security.…”

“…Furthermore, it may be impractical to employ traditional DL frameworks in applications with privacy sensitive training data [39], [87]. Hence, a lot of research work is being done to implement decentralized learning frameworks, in which all the private data is kept where it is generated and only locally trained models are transferred to a central entity [24], [37], [39], [87]- [90].…”

“…Although the FL frameworks present promising results, the technique of FL has two main challenges. The technique suffers from the limitations of massive communication overhead and non-IID data [90], [148]. This is mainly because the accuracy of FL algorithms is significantly reduced when highly non-IID data is used as compared to when IID data is used.…”

“… Reducing the total number of updates transferred for each UE. Therefore, [37], [90], [138], [145], [146]- [148] presented various mechanisms to address the challenge of massive communication overhead in FL. For instance, to address the challenges of the traditional FedAvg algorithm, novel FL frameworks were proposed in [138], [142], [146], [147].…”

“Chatty Devices” and Edge-based Activity Classification

“…By implication, this raises concerns around privacy, security and scale of data. Recent approaches to achieve this include Federated Learning, which can be used to train a globally shared model by exploiting a massive amount of user-generated data samples on sen-sorized/ chatty devices while preventing data leakage [49]. A surrogate model is developed on each device, which can then be combined at a cloud data centre.…”