We are pleased to share some news from the 2023 IEEE Future Networks World Forum (FNWF) in Baltimore, MD, USA. Our paper, mmWave Beam Selection in Analog Beamforming Using Personalized Federated Learning was awarded the Best Paper Award. This recognition is both humbling and encouraging for us as researchers.
Long LaTeX build times can be a significant challenge for researchers and developers, hampering productivity and efficiency. This issue arises due to the complexity of LaTeX documents and the diversity of build systems available. We present a comprehensive exploration of LaTeX build systems, helping authors choose the most suitable one. By identifying the best build system, authors can streamline their workflow, reduce build times, and ultimately enhance their research and development endeavors.
LaTeX, a typesetting system celebrated for its capacity to effortlessly blend visual appeal with practicality, remains an essential instrument for both researchers and academics. While its inherent capabilities are impressive, the full potential of LaTeX is revealed through the skillful utilization of its macros. As a researcher in the field of artificial intelligence, I find that I am very often using a set of LaTeX commands, macros and definitions when writing academic papers, and perhaps you will find them useful too.
If you have submitted or plan to submit your paper to an IEEE journal or conference, you might want to consider posting your pre-print in arXiv.org or TechRxiv.org, on your employer’s website or institutional repository and on your personal website. IEEE does not consider this to be a form of prior publication, see IEEE Post-Publication Policies. But what are the practical steps to do so? In this post we cover the mandatory steps you have to take in order to publish an IEEE article as a pre-print.
Federated Learning (FL) is a promising framework for distributed learning when data is private and sensitive. However, the state-of-the-art solutions in this framework are not optimal when data is heterogeneous and non-Independent and Identically Distributed (non-IID). We propose a practical and robust approach to personalization in FL that adjusts to heterogeneous and non-IID data by balancing exploration and exploitation of several global models. To achieve our aim of personalization, we use a Mixture of Experts (MoE) that learns to group clients that are similar to each other, while using the global models more efficiently. We show that our approach achieves an accuracy up to 29.78 % and up to 4.38 % better compared to a local model in a pathological non-IID setting, even though we tune our approach in the IID setting.
Tables in scientific papers often look less than professional, and sometimes this can even get in the way of understanding the message. In this blog post we will learn how to add sparklines to a LaTeX table, which not only makes your table stand out, but also allows for conveying information about for example trends in time-series.