Paper Presentation

Graph Neural Networks on Quantum Computers

- By Yidong Liao, PhD student, University of Technology Sydney (UTS)

Download the Research Paper

Explore the future of machine learning at the intersection of quantum computing and graph theory in this session with Yidong Liao, author of Graph Neural Networks on Quantum Computers. Graph Neural Networks (GNNs) are increasingly used to analyze complex, structured data across fields such as social networks, biology, and recommendation systems. However, classical GNNs often struggle with scalability, especially when applied to large datasets.

Yidong will introduce innovative frameworks for implementing GNNs on quantum computers, showcasing how quantum computing can potentially address these scalability challenges. By adapting popular GNN architectures—like Graph Convolutional Networks and Message-Passing GNNs—this research paves the way for more efficient data processing in graph-based machine learning. Join us for a forward-looking discussion on how quantum advancements could transform AI applications.


Meet our Speaker:

Yidong Liao

Yidong Liao is a PhD student at the Centre for Quantum Software and Information, University of Technology Sydney (UTS), under the supervision of A/Prof. Chris Ferrie. His work explores innovative approaches to quantum neural network architecture design and quantum-optimization-powered training methodology, with a particular interest in integrating state-of-the-art classical AI models like GPT and Graph Neural Networks (GNNs) with quantum computing. He completed his Master's degree at the University of Queensland (UQ).