XClose

Institute of Communications and Connected Systems

Home
Menu

ICCS Researcher receives Google Research Scholar Program Award

9 June 2023

Dr Ilija Bogunovic, Lecturer in Institute of Communications and Connected Systems (ICCS) at EEE makes history as the first researcher from UCL to receive the Google Research Scholar Program Award.

Ilija Bogunovic profile pic

Graph neural networks (GNNs) have emerged as a promising class of machine learning models that excel in various prediction tasks and applications, including the design of novel materials, drug discovery, structure-based protein function prediction, system-on-chip design, and more. These applications often involve the exploration of graph-based designs where the objective is to identify the best design through a limited number of costly trials or experiments.

Dr Ilija Bogunovic’s work specialises in integrating graph neural networks into real-world experimentation. By leveraging the inherent structure of graphs and harnessing GNN surrogate models, his work seeks to harness the insights gained from past trials to enhance the efficiency and effectiveness of real-world experiments. In the context of molecule design, his work can be directly applied to suggest new candidate molecules for real-world evaluation based on the outcomes of previous experiments, minimising the number of costly trials required.

Established in 2021, the Google Research Scholar Program aims to support early-career professors who are pursuing research in fields relevant to Google. The program is one of the many outreach initiatives introduced by Google to support the development of collaborations among early career researchers and encourage the formation of long-term relationships within the academic community. All recipients are granted funds up to $60,000 USD, intended to support the advancement of the recipient’s research.

Speaking on his thoughts on winning the award, Dr Bogunovic further elaborated,

With the award, I intend to further advance the field of machine learning with graph-structured data and its application to real-world experimentation. The recognition and financial support provided by the award will allow me to delve deeper into the development and refinement of graph neural networks (GNNs) as powerful surrogate models for sequential decision-making tasks. I plan to conduct extensive research to optimize the performance and efficiency of GNN model-based optimization in various domains (e.g., material design, molecular optimization, and chip design). Additionally, I will collaborate with experts in these fields to explore novel applications and establish partnerships to facilitate the practical implementation of GNN-based surrogate models in real-world settings. Ultimately, my goal is to make significant contributions to the advancement of data-driven experimentation and empower scientists and researchers with valuable tools to accelerate the discovery and design processes.

Dr Bogunovic, the first researcher from UCL to be granted this award, shares this recognition with 77 other early-career researchers across the globe with research interests in fields including algorithms and optimization, human-computer interaction, machine learning and data mining, natural language processing, privacy, quantum computing, security, and systems.

Reflecting on this unique achievement, Professor Izzat Darwazeh, Director of UCL ICCS and Chair of Communications Engineering and Head of Information and Communication and Engineering (ICE) Group commented,

Being awarded the prestigious Google Research Scholar Program reflects the exceptional contributions Dr Bogunovic can offer to the field of machine learning. His achievements exemplify our group's commitment to pushing the boundaries of data-driven experimentation and propelling the field forward. By empowering scientists and researchers with invaluable tools to accelerate the discovery and design processes, his work will undoubtedly have a profound impact on the field. We are excited to witness the continued success of his research, as it shapes the future of machine learning and real-world experimentation.

Links