Abstract
Federated learning (FL) is a new technology that has been a hot research topic. It enables the training of an algorithm across multiple decentralized edge devices or servers holding local data samples without exchanging them. There are many application domains in which considerable properly labeled and complete data are not available in a centralized location (e.g., doctors’ diagnoses from medical image analysis). There are also growing concerns over data and user privacy, as artificial intelligence is becoming ubiquitous in new application domains. As such, much research has recently been conducted in several areas within the nascent field of FL. Various surveys on different subtopics exist in the current literature, focusing on specific challenges, design aspects, and application domains. In this paper, we review existing contemporary works in related areas to understand the challenges and topics emphasized by each type of FL survey. Furthermore, we categorize FL research in terms of challenges, design factors, and applications, conducting a holistic review of each and outlining promising research directions.
Highlights
In recent years, machine learning (ML) technologies have seen tremendous growth
Due to concerns over data ownership and data confidentiality, user privacy, and new laws over data management and data usage like General Data Protection Regulation (GDPR), there is a need for distributed model training in a private, secure, efficient and fair way
Focusing on IoT, covers works related to Federated Learning (FL) challenges and privacy preserving methods, identify the strengths and weaknesses of different methods applied to FL, and outlines future directions
Summary
Machine learning (ML) technologies have seen tremendous growth. The availability of large amounts of data is one of the reasons for this rapid growth of ML and Deep Learning (DL) based techniques/methods. This resulting joint model’s performance is an approximation of the ideal model trained with centralized data. The surveys cover a variety of domains and focus areas in FL research Several core challenges such as privacy, security, communication cost, system and statistical heterogeneity, architecture and aggregation algorithm designs, etc. We classify the topics in the FL survey papers according to the following categories: communication cost, statistical heterogeneity, systems heterogeneity, privacy/security as the core challenges; data partitioning, FL architectures, algorithms/aggregation techniques, personalization techniques as the implementation details; and applications of FL in different industries and domains. 3) Conducted a holistic survey of the design aspects – data partitioning, FL architectures, aggregation techniques, personalization techniques; the core challenges – communication cost, systems heterogeneity, statistical heterogeneity, privacy/security; and, different application areas.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
