Shirui Pan is a Professor and an ARC Future Fellow with the School of Information and Communication Technology, Griffith University, Australia. Before joining Griffith in August, 2022, he was with the Faculty of Information Technology, Monash University between Feb 2019 and July 2022. He received his Ph.D degree in computer science from University of Technology Sydney (UTS), Australia.
Shirui has made contributions to advance graph machine learning methods for solving hard AI problems for real-life applications, including graph classification, anomaly detection, recommender systems, and multivariate time series forecasting. His research has been published in top conferences and journals including NeurIPS, ICML, KDD, TPAMI, TNNLS, and TKDE. He is recognised as one of the AI 2000 AAAI/IJCAI Most Influential Scholars in Australia (2021, 2022), and one of the World’s Top 2% Scientists (2021). His research received the IEEE ICDM Best Student Paper Award (2020), and the JCDL Best Paper Honorable Mention Award (2020). He has eight papers recognised as the Most Influential Papers in KDD (x1), IJCAI (x5), AAAI (x1), and CIKM (x1) (Feb 2022). He received a prestigious Future Fellowship (2022-2025), one of the most competitive grants from the Australian Research Council (ARC).
PhD positions are open! I am looking for self-motivated Ph.D students. See more information here.
PhD in Computer Science
University of Technology Sydney
Human knowledge provides a formal understanding of the world. Knowledge graphs that represent structural relations between entities have become an increasingly popular research direction towards cognition and human-level intelligence. In this survey, we provide a comprehensive review on knowledge graph covering overall research topics about 1) knowledge graph representation learning, 2) knowledge acquisition and completion, 3) temporal knowledge graph, and 4) knowledge-aware applications, and summarize recent breakthroughs and perspective directions to facilitate future research. We propose a full-view categorization and new taxonomies on these topics. Knowledge graph embedding is organized from four aspects of representation space, scoring function, encoding models and auxiliary information. For knowledge acquisition, especially knowledge graph completion, embedding methods, path inference and logical rule reasoning are reviewed. We further explore several emerging topics including meta relational learning, commonsense reasoning, and temporal knowledge graphs. To facilitate future research on knowledge graphs, we also provide a curated collection of datasets and open-source libraries on different tasks. In the end, we have a thorough outlook on several promising research directions.
Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic. A basic assumption behind multivariate time series forecasting is that its variables depend on one another but, upon looking closely, it’s fair to say that existing methods fail to fully exploit latent spatial dependencies between pairs of variables. In recent years, meanwhile, graph neural networks (GNNs) have shown high capability in handling relational dependencies. GNNs require well-defined graph structures for information propagation which means they cannot be applied directly for multivariate time series where the dependencies are not known in advance. In this paper, we propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module, into which external knowledge like variable attributes can be easily integrated. A novel mix-hop propagation layer and a dilated inception layer are further proposed to capture the spatial and temporal dependencies within the time series. The graph learning, graph convolution, and temporal convolution modules are jointly learned in an end-to-end framework. Experimental results show that our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets and achieves on-par performance with other approaches on two traffic datasets which provide extra structural information..
IEEE TPAMI, TNNLS, TKDE, TCYB; ICML, NeurIPS, KDD, WWW, CVPR, WSDM, ICDM, AAAI, IJCAI
Shirui Pan’s research was supported by Australian Research Council (ARC), Defence Science and Technology Group (DSTG), Amazon, Metso Outotec, Shanghai Aircraft Manufacturing Co, Ltd, etc.
[Award]: Amazon Research Awards (APA) Fall 2021 round.
[Award]: AI 2000 AAAI/IJCAI Most Influential Scholars Honorable Mention (2022) (only three recipients in Australia) (25/01/2021).
[Award]: Enabling Automatic Graph Learning Pipelines with Limited Human Knowledge ($800,000 from ARC and $470,000 from Monash University) - 2021-2025
[Award]: 5 Papers are Selected as Most Influential Papers in IJCAI (02/2022).
[Award]: 1 Paper is Selected as Most Influential Paper in KDD (02/2022).
[Award]: 1 Paper is Selected as Most Influential Paper in AAAI (02/2022).
[Award]: 1 Paper is Selected as Most Influential Paper in CIKM (02/2022).
[Award]: 2021 FIT Dean’s Award for Excellence in Research by an Early Career Researcher
[Award]: AI 2000 AAAI/IJCAI Most Influential Scholars Honorable Mention (2021) (only five recipients in Australia) (08/04/2021).
Best Student Paper Award for ICDM-2020 (CORE A* conference)
The Vannevar Bush Best Paper Honorable Mention for JCDL-2020 (CORE-2018 A* conference)
Anomaly Detection in Social Networks ($11,000) - 2019-2020
Cyberbullying Detection on Social Networks ($20,000) - 2016-2017