Robust Federated Learning for Imperfect Decentralised Data

Project Member(s): Long, G., Jiang, J.

Funding or Partner Organisation: Australian Research Council (ARC Discovery Projects)
Australian Research Council (ARC Discovery Projects)

Start year: 2022

Summary: This project aims to develop a next-generation heterogeneous federated learning framework that is robust enough to tackle a broad range of challenging scenarios in real applications, e.g., mobile devices and IoT. This project expects to advance the development of cutting edge techniques to develop new intelligent applications in decentralized and privacy-sensitive scenarios. The expected outcomes of this project include a new tool ready for use. This should provide significant benefits to a broad range of industry sectors. This game-changing research will help to transform current data mining and deep learning research from centralised intelligence with big data to decentralised intelligence with collaborative training and big network.

FOR Codes: Mobile technologies and communications, Artificial intelligence, Machine learning, Data mining and knowledge discovery

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.