Winner, Outstanding Research Contribution Award
Jia Wu has made impressive contributions to the areas of data mining and artificial intelligence, with a particular focus on graph mining. Within the last four years, Jia has made significant advancements in graph mining theories and techniques, notably designing a subgraph neural network for brain disorder exploration and enhancing graph neural network interpretability through a deep evolutionary framework. His contributions across graph learning paradigms are widely adopted as field baselines. Jia’s research extends beyond academia through collaborations with leading Australian industries, including CSIRO and Domain Holdings. As Research Director of the Applied AI Centre, Macquarie University, he has secured nearly $10 million in funding since 2021, showcasing his leadership and societal impact.
Presentation Title: Advancing Graph Mining Techniques for Complex Structures
Abstract: Graph mining has emerged as a key technology in analysing and understanding data with complex structures, driving advancement in diverse applications such as social networks, molecular biology, brain science, and urban planning. However, traditional methods primarily focus on node-level or edge-level interactions within isolated graphs, limiting their applicability to complex, real-world data environments. This research seeks to advance graph mining techniques by addressing these challenges, introducing innovative methods for handling graph complexities and ensuring robustness in diverse scenarios. The proposed techniques are evaluated on real-world datasets, demonstrating superior performance in efficiency and effectiveness compared to state-of-the-art methods. The research contributes to the broader field of data science and AI, offering practical tools and insights to address critical challenges in graph mining, and laying the foundation for new applications in understanding and modelling complex structured data.