Lecture: 'Federated learning future, challenges, and applications'

We live in a data-driven era where AI and ML, diverse and distributed data sources, are integrated into every aspect of life and industry. While this approach empowers applications to provide better services and user experiences, it imposes serious debate on data and client privacy, specifically on data protection regulations and restrictions such as EU GDPR. Moreover, collecting, aggregating, and integrating heterogeneous data dispersed over various data sources and securely managing and processing the data are non-trivial tasks. The challenges are not only due to transporting high-volume, high-velocity, high-veracity, cybersecurity attacks, and heterogeneous data across organizations. In this context, Federated learning (FL) has emerged as a prospective solution to address these issues by enabling collaborative learning without compromising data privacy. FL locates ML operations closer to clients, making it crucial for intelligent applications like autonomous driving, smart manufacturing, and healthcare. FL has gained significant attention in the machine learning community due to its potential impact on future developments.

In this talk, I will give a general idea about FL, Challenges, Applications, FEDn, and Open research problems. The presentation targets a general audience with basic computer science and artificial intelligence knowledge.

About

SADI ALAWADI received his Ph.D. degree in Computer science/AI from the Research Center of Intelligent Technologies (CiTIUS)-University of Santiago de Compostela, Spain, in 2018, and a Master degree in Softcomputing and intelligence system, 2012, from Granada University. He is currently working as an Assistant Professor at Halmstad University, Sweden. Previously, he worked as a Postdoctoral Researcher at the Department of Information Technology, Division of Scientific Computing, Uppsala University, Postdoctoral Researcher IOTAP Research Center - Malmö University, and Postdoctoral Researcher at the Consiglio Nazionale delle Ricerche (CNR) - ISTI, Pisa, Italy. He has several publications in top journals and conferences, including Neural Networks, IEEE TEM, IEEE TII, INFSOF, NCA,JKSUCIS, CCGRID etc. His main research interests include Internet of Things (IoT), Machine Learning (ML), Deep learning, Real-time analysis, Data visualizations, Bigdata, Digital forensics, Edge and Cloud computing, Dimensionality reduction, Blockchain, Federated learning, Transfer and interactive learning, and Internet of Health.