Structure Search Over Large Scale Heterogeneous Information Networks
2020 - 2022, Xuemin Lin, $540,000
This project aims to develop novel mathematical frameworks for probabilistic geophysical imaging and inference, building on recent advances in statistics and machine learning. These will allow us to obtain a more detailed and robust understanding of structures and processes occurring within the Earth, including those relevant to the Australian minerals and/or energy industries. Outcomes of this research include mathematical and computational tools for imaging the subsurface, and greater understanding of Australian and global geoscience. This work can permit more effective exploitation of earth resources, as well as improving our understanding of how the Earth system has developed over geological history.
Cohesive Subgraph Discovery on Big Bipartite Graphs
2020 - 2022, Wenjie Zhang, $430,000
This project aims to develop novel technology for efficient and scalable cohesive subgraph discovery on big bipartite graphs, including new theories, indexing techniques, and data processing algorithms. We anticipate addressing key challenges and laying scientific foundations of big graph computation, as well as delivering high-impact technologies. The success of the project will directly benefit the key applications in Australia such as cyber-security, health, bio-informatics, social networks, and E-commerce. The success of the project will also facilitate the training of PhD graduates and postdoctoral research associates in the area of Big Data.
Efficient Processing of Large Scale Multi-dimensional Graphs
2018 - 2020, Xuemin Lin, Wenjie Zhang and Ying Zhang, $407,974
This project aims to develop novel approaches to process large scale multi-dimensional graphs. The project will focus on the three most representative types of problems against multi-dimensional graphs, namely cohesive subgraph computation, frequent subgraph mining, and subgraph matching. The project outcome will include a set of new theories, novel indexing and data processing techniques, including distributed and single node computation. The success of the project will significantly contribute to the technology development and the scientific foundation of big graph processing.