Ming Jin |
I am currently an Assistant Professor at
School of Information and Communication Technology (ICT), Griffith University.
Before this, I was a Research Assistant in the Faculty of Information Technology at Monash University, where I also obtained my Ph.D. degree in 2024.
I specialize in time series analysis and spatio-temporal data mining, with a good track record of publishing high-impact papers in top-ranked venues, including NeurIPS, ICLR, ICML, KDD, and IEEE TPAMI, among others.
One of my research was selected as one of the most influential IJCAI papers by PaperDigest (2022-05), and another received 200+ citations and 1.3K+ GitHub stars within few months.
I have also served as an Associate Editor for Journal of Neurocomputing (Q1; IF=6.0) and frequently as an Area Chair/PC member for prestigious conferences and workshops, such as NeurIPS (incl. TGL), ICLR, ICML, KDD (incl. MiLeTS), IJCAI (incl. AI4TS), AAAI, and more.
I am dedicated to conducting high-impact research and open for collaborations. My research interests are broadly in (1) time series analysis, (2) graph neural networks, and (3) multimodal learning, with a special focus on temporal settings (e.g., GNNs & FMs & LLMs for time series and spatio-temporal data) in solving both fundamental and real-world problems.
- Multiple Ph.D. positions are available. I am looking for well-matched, qualified, and self-motivated candidates to work with me. If you are interested, drop me an email with your application materials. See more information here about our lab.
Scaling to Billion Parameters for Time Series Foundation Models with Mixture of Experts |
|
A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, |
|
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models |
|
Position: What Can Large Language Models Tell Us about Time Series Analysis |
|
Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective |
|
Foundation Models for Time Series Analysis: A Tutorial and Survey |
|
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects |
|
A Survey on Diffusion Models for Time Series and Spatio-Temporal Data |
|
HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling for Long-Term Forecasting |
|
Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook |
|
Neural Temporal Walks: Motif-Aware Representation Learning on Continuous-Time Dynamic Graphs |
|
Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs |
|
Graph Self-Supervised Learning: A Survey |
|
ANEMONE: Graph Anomaly Detection with Multi-Scale Contrastive Learning |
|
ANEMONE: Graph Anomaly Detection with Multi-Scale Contrastive Learning |
|
Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning |
a) Conferences:
b) Journals: