Foundation Models and Federated Learning research group

Author: Guodong Long, Australian Artificial Intelligence Institute, University of Technology Sydney, Australia Date: Feb 12, 2026 Will Federated Learning Be the Next Breakthrough for Time-Series Foundation Models? Federated learning has long been viewed primarily as a privacy-preserving technique . However, its true essence lies in something deeper: the intrinsic capability for collaboration among distributed participants . When we shift our perspective from privacy to collaboration, a more ambitious vision of federated learning emerges — and with it, new possibilities for innovation. Let us momentarily set aside privacy preservation and explore a broader question: Could federated learning unlock the next generation of time-series foundation models? If this sparks ideas for papers, grants, or applications, I would be delighted to discuss further. A Brief History of Time-Series Foundation Models Foundation models are pre-trained machine learning models designed to capture general knowle...

Author: Guodong Long, Australian Artificial Intelligence Institute, University of Technology Sydney, Australia Date: Feb 12, 2026 What Is Federated Recommendation? Federated recommendation is an emerging approach to building recommendation systems using a federated learning (FL) framework , with privacy preservation as a core principle. Traditional recommendation systems are typically operated by centralized servers controlled by service providers. These systems require users’ interaction data—such as viewing history, browsing behavior, and purchase records—to be stored and processed on the provider’s servers. In contrast, federated recommendation shifts data storage and model training to users’ local devices (e.g., smartphones or personal computers). Rather than uploading raw behavioral data to centralized servers, the model is trained locally, and only privacy-preserving updates are shared with the service provider. This reduces the exposure of sensitive personal information while m...

Author: Guodong Long, Australian Artificial Intelligence Institute, University of Technology Sydney, Australia Date: Feb 12, 2026 Federated learning (FL) is a privacy-preserving machine learning paradigm designed to enable collaborative model training across distributed data sources without centralising sensitive data. It has been widely adopted in domains involving personal devices (e.g., smartphones) and data-sensitive institutions, particularly healthcare and finance. National Infrastructure and Major Investments In 2023, a A$13.7 million initiative ( link ), titled NINA – National Infrastructure for Federated Learning in Digital Health , was established and is hosted by the Faculty of Health at The University of Queensland (UQ). Led by Professor Clair Sullivan (UQ) , the project received A$6 million from the Medical Research Future Fund (MRFF) under the National Critical Research Infrastructure scheme. This investment reflects growing national commitment to federated learning as a...