Advancing federated learning for unified urban spatio-temporal predictions

This project aims to develop an advanced learning system for training urban spatio-temporal foundation models that can achieve robust zero- and few-shot generalisation across diverse datasets, cities, and urban domains. The proposed system will integrate large-scale heterogeneous urban data—such as mobility, traffic, environmental, and infrastructure signals—into a unified modelling framework that captures complex spatial dependencies and long-term temporal dynamics.

To overcome the fragmentation and limited transferability of existing urban analytics models, you will investigate novel representation learning, pre-training, and adaptation strategies tailored to urban spatio-temporal data. In particular, you will focus on learning universal urban representations that can be efficiently transferred to new cities, tasks, or data regimes with minimal or no additional supervision.

You will also explore federated and resource-efficient learning mechanisms to enable scalable and privacy-preserving model training across distributed data sources. 

The University of Queensland, Brisbane, Australia, is a world's top 50 university (QS World University Rankings 2025). Embedded in the Data Science discipline at The University of Queensland, you will be part of a world-leading research group in Data Science and AI with research funding coming both from the industry sector (e.g., Amazon, Meta, Google) and the public sector (e.g., the Australian Research Council).

This project is supported by the Research project scholarship.

Learn more about the Research project scholarship.

Your application will be assessed on a competitive basis.

We take into account your:

• previous academic record
• publication record
• honours and awards
• employment history.

A working knowledge of Large Language Models, Foundation Model, Agentic AI, Multi-Agent, Graph Learning, Spatio-temporal Forecasting, and/or Federated Learning would be of benefit to someone working on this project.

You will demonstrate academic achievement in the fields of Computer Science or Data Science or AI and the potential for scholastic success.

A background or knowledge of Data Science and AI is highly desirable.

You must submit an expression of interest (EOI) by 14 August, 2026 14 August, 2026.

Before you apply

1. Check your eligibility for the Doctor of Philosophy (PhD).
2. Prepare your documentation.
3. If you have any questions about whether the project is suitable for your research interests, contact Professor Hongzhi Yin (h.yin1@uq.edu.au).

When you apply

To apply, submit an expression of interest (EOI) for the program. You don't need to apply separately for the project or scholarship. How to submit an EOI

In your EOI, complete the ‘Scholarship/Sponsorship’ section with the following details:

1. Are you applying for an advertised project: 'Yes'
2. Project: 'Research project scholarship'
3. Scholarship Code Listed in the Advertisement: FEDERATED-YIN
4. Link to Scholarship Advertisement: https://study.uq.edu.au/study-options/phd-mphil-professional-doctorate/projects/advancing-federated-learning-unified-urban-spatio-temporal-predictions

Submit an EOI