Shirui Pan

Professor and ARC Future Fellow

Biography

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 2022, he was Senior Lecturer (Associate Professor) with the Faculty of Information Technology, Monash University. He received his Ph.D degree in computer science from University of Technology Sydney (UTS), Australia. He is a Senior Member of IEEE and ACM, and a Fellow of Queensland Academy of Arts and Sciences (FQA).

His research focuses on artificial intelligence and machine learning. His research was cited 20,077 times, H-Index: 50 (on September 23, 2023).

He 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 (2023, 2022), and one of the World’s Top 2% Scientists (2022, 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).

潘世瑞（中文简介）

博士招生信息（2023年1月更新）

PhD positions are open! I am looking for self-motivated Ph.D students. See more information here.

Interests

Artificial Intelligence
Data Mining
Machine Learning
Deep Learning
NLP
Graph Neural Networks
Trustworthy AI

Education

PhD in Computer Science

University of Technology Sydney

What’s New

[Paper]: Three papers on graph neural networks were accepted at NeurIPS-23 (09/2023).
[Award]: We received the 2024 IEEE CIS TNNLS Outstanding Paper Award for our GNN research published in 2021 (with 6200+ Citations)(07/2023).
[Paper]: A Roadmap on Unifying LLMs and Knowledge Graphs is released (04/2023).
[Tutorial]: A tutorial on Graph Self-supervised Learning presented at IJCNN-2023 (07/2023).
[Paper]: One paper on knowledge graph was accepted by ACL-2023 (04/2023).
[Paper]: Four papers on graph neural networks were accepted in top conferences: ICML-23 (x2), SIGIR-23 (x1), and IJCAI-23 (x1) (04/2023).
[Award]: Elected as Fellow of Queensland Academy of Arts and Sciences (QAAS). The QAAS Fellowship recognises significant eminence and contributions to the arts and sciences as a practitioner (02/2023).
[Paper]: Four papers on graph neural networks were accepted by WWW-2023 (01/2023).
[Editorial Board]: I am invited to serve as an Associate Editor for IEEE Transactions on Cybernetics (TCYB) (IF: 19.11) (12/2022).
[Editorial Board]: I am invited to serve as an Associate Editor for Neural Networks (IF: 9.657) and Knowledge and Inforamtion Systems(IF: 2.531) (12/2022).
[Paper]: Three papers on graph neural networks were accepted by AAAI-2023 (11/2022).
[PhD Completion]: Congratulations to Man Wu for passing her PhD thesis defense. Her PhD research outcomes include 2xICDM, 1xWWW, 1xKAIS, 1xTKDD, 1xTETCI, 1xNature Scientific Report.
[Paper]: Three papers on graph neural networks were accepted by NeurIPS-2022 (15/09/2022).
[Award]: I am honoured to receive an Amazon Research Award (APA) (27/08/2022).
[Job Updated]: I left Monash University on July 27, 2022 and I joined Griffith University as a Professor on August 1st (Updated on 01/08/2022).
[Google PhD Fellowship]: Congratulations to Yixin Liu receiving 2022 Google PhD Fellowship.
[Paper]: One paper was accepted by ACM Computing Surveys (15/06/2022), work led by a Monash Master’s student.
[Paper]: One paper was accepted by KDD-2022 (19/05/2022) (Acceptance Rate: 15%).
[PhD Completion]: Congratulations to Shichao Zhu for passing her PhD thesis defense.
[Paper]: Four papers were accepted by AAAI-2022 (10/04/2022).
- two papers as Long Oral Presentation (Acceptance Rate: 3.75%)
- one paper as Short Oral Presentation (Acceptance Rate: 15%)
- one paper as Survey Paper (Acceptance Rate: 18%)
[Paper]: Three papers were accepted by CVPR-2022 (02/03/2022).
[Paper]: One paper was accepted by IEEE TPAMI (19/01/2022).
[Paper]: Two papers were accepted by WWW-22 (14/01/2022).
[Paper]: Two papers were accepted by SDM-22 (19/12/2021).
[Paper]: One paper was accepted by AAAI-22 (Acceptance rate: 15%)(07/12/2021).
[Paper]: One paper was accepted by WSDM-22 (12/10/2021).
[Paper]: One paper on Graph Poisson Networks was accepted by NeurIPS-21 (28/09/2021).
[Award]: ARC Future Fellowship (only five recipients in Computer Science in Australia in 2021) (11/08/2021).
[PhD Completion]: Congratulations to Miao Zhang, Zonghan Wu, Chun Wang, Guojia Wan, who have finished/submitted their final theses in 2021. It was my fortune to have worked with them!(08/2021).
[Award]: AI 2000 AAAI/IJCAI Most Influential Scholars Honorable Mention (only five recipients in Australia) (08/04/2021).
[Award]: 3 Papers are Selected as Most Influential Papers in IJCAI (08/03/2021).
- 2019 Graph WaveNet For Deep Spatial-Temporal Graph Modeling (Rank: 2)
- 2018 Adversarially Regularized Graph Autoencoder For Graph Embedding (Rank: 7)
- 2016 Tri-Party Deep Network Representation (Rank: 6)
[Award]: 1 Paper is Selected as Most Influential Paper in KDD (08/03/2021).
- 2020 Connecting The Dots: Multivariate Time Series Forecasting With Graph Neural Networks (Rank: 7)
[Award]: 1 Paper is Selected as Most Influential Paper in AAAI (08/03/2021).
- 2018 DiSAN: Directional Self-Attention Network For RNN/CNN-Free Language Understanding (Rank: 10)
[Award]: 1 Paper is Selected as Most Influential Paper in CIKM (08/03/2021).
- 2017 MGAE: Marginalized Graph Autoencoder For Graph Clustering (Rank: 11)
[Paper]: One paper on Knowledge Graph was accepted by IEEE T-NNLS as a Survey Paper (CORE A*, IF:8.793)(19/03/2021)
[Paper]: One paper on Graph Learning was accepted by IEEE Transactions on Artificial Intelligence as a Survey Paper (28/03/2021)
[Paper]: One paper on Graph Anomaly Detection was accepted by IEEE T-NNLS as a Regular Paper (CORE A*, IF:8.793)(19/03/2021)
One paper on graph neural networks was accepted by ACM Transactions on Knowledge Discovery from Data (TKDD) (08/02/2021).
One paper was accepted by The Web Conference (WWW-21) (16/01/2021).
[Paper]: A Survey on Community Detection was released (Click Here )(06/01/2021).
[Paper]: One paper on Contrastive Graph Learning was accepted by AAAI-21 (02/12/2020).
[Award]: The Best Student Paper Award at ICDM-2020 for Open-World Graph Learning (13/11/20).
[Paper]: One paper on Neural Architecture Search was accepted by IEEE TPAMI as a Regular Paper (CORE A*, IF: 17.86)(27/10/2020) (Top Journal in AI)
[Paper]: Three papers were accepted by NeurIPS-2020 as full papers (CORE A*, Acceptance Rate: 20%)(26/09/2020) (Top Conference in Machine Learning)
1. Graph Geometry Interaction Learning
2. Graph Stochastic Neural Networks
3. Exploration Enhancing Neural Architecture Search (E^2NAS)
[Paper]: Two papers are accepted by KDD-2020 (16/05/2020) (Acceptance Rate: 16.9%).
1. Connecting the Dots: GNN for Time Series
2. Zero-shot Event Captioning

Featured Publications

Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, Xindong Wu

August, 2023 Preprint arXiv:2306.08302

Unifying Large Language Models and Knowledge Graphs: A Roadmap

Large language models (LLMs), such as ChatGPT and GPT4, are making new waves in the field of natural language processing and artificial intelligence, due to their emergent ability and generalizability. However, LLMs are black-box models, which often fall short of capturing and accessing factual knowledge. In contrast, Knowledge Graphs (KGs), Wikipedia and Huapu for example, are structured knowledge models that explicitly store rich factual knowledge. KGs can enhance LLMs by providing external knowledge for inference and interpretability. Meanwhile, KGs are difficult to construct and evolving by nature, which challenges the existing methods in KGs to generate new facts and represent unseen knowledge. Therefore, it is complementary to unify LLMs and KGs together and simultaneously leverage their advantages. In this article, we present a forward-looking roadmap for the unification of LLMs and KGs. Our roadmap consists of three general frameworks, namely, 1) KG-enhanced LLMs, which incorporate KGs during the pre-training and inference phases of LLMs, or for the purpose of enhancing understanding of the knowledge learned by LLMs; 2) LLM-augmented KGs, that leverage LLMs for different KG tasks such as embedding, completion, construction, graph-to-text generation, and question answering; and 3) Synergized LLMs + KGs, in which LLMs and KGs play equal roles and work in a mutually beneficial way to enhance both LLMs and KGs for bidirectional reasoning driven by both data and knowledge. We review and summarize existing efforts within these three frameworks in our roadmap and pinpoint their future research directions.

Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Xiaojun Chang, Chengqi Zhang

May, 2020 ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD-20

Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks

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..

See all publications

Recent Publications

IEEE TPAMI, TNNLS, TKDE, TCYB; ICML, NeurIPS, KDD, WWW, CVPR, WSDM, ICDM, AAAI, IJCAI

Selected Pubs (IEEE Trans/CORE A*); Full Publications; Seleted Publications in GNNs.

Xin Zheng, Miao Zhang, Chunyang Chen, Soheila Molaei, Chuan Zhou, Shirui Pan (2023). GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels. Advances in Neural Information Processing Systems, NeurIPS, New Orleans, USA, 10 Dec 2023 – 16 Dec, 2023 (CORE A*).

Xin Zheng, Miao Zhang, Chunyang Chen, Quoc Viet Hung Nguyen, Xingquan Zhu, Shirui Pan (2023). Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data. Advances in Neural Information Processing Systems, NeurIPS, New Orleans, USA, 10 Dec 2023 – 16 Dec, 2023 (Spotlight)(CORE A*).

PDF

Yixin Liu, Kaize Ding, Qinghua Lu, Fuyi Li, Leo Yu Zhang, Shirui Pan (2023). Towards Self-Interpretable Graph-Level Anomaly Detection. Advances in Neural Information Processing Systems, NeurIPS, New Orleans, USA, 10 Dec 2023 – 16 Dec, 2023 (CORE A*).

Zicheng Zhao, Linhao Luo, Shirui Pan, Quoc Viet Hung Nguyen, Chen Gong (2023). Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A Relational Anonymous Walk-guided Neural Process Approach. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML/PKDD, September 18 -22 2023, Turin, Italy (CORE A).

PDF

Xiao Shen, Mengqiu Shao, Shirui Pan, Laurence Yang, Xi Zhou (2023). Domain-adaptive Graph Attention-supervised Network for Cross-network Edge Classification. IEEE Transactions on Neural Networks and Learning Systems (TNNLS).

Xixun Lin, Chuan Zhou, Jia Wu, Lixin Zou, Shirui Pan, Yanan Cao, Bin Wang, Shuaiqiang Wang, Dawei Yin (2023). Towards Flexible and Adaptive Neural Process for Cold-Start Recommendation. IEEE Transactions on Knowledge and Data Engineering (TKDE).

PDF

Yixin Liu, Kaize Ding, Jianling Wang, Vincent Lee, Huan Liu, Shirui Pan (2023). Learning Strong Graph Neural Networks with Weak Information. 29th SIGKDD Conference on Knowledge Discovery and Data Mining, KDD-23, 6 Aug 2023 – 10 Aug 2023, Long Beach, California, United States (CORE A*).

PDF

Di Jin, Luzhi Wang, He Zhang, Yizhen Zheng, Weiping Ding, Feng Xia, Shirui Pan (2023). A Survey on Fairness-aware Recommender Systems. Information Fusion.

PDF

Dongran Yu, Bo Yang, Dayou Liu, Hui Wang, Shirui Pan (2023). A Survey on Neural-symbolic Learning Systems. Neural Networks Journal.

PDF

Sheng Wan, Yibing Zhan, Shuo Chen, Shirui Pan, Jian Yang, Dacheng Tao, Chen Gong (2023). Boosting Graph Contrastive Learning via Adaptive Sampling. IEEE Transactions on Neural Networks and Learning Systems (TNNLS).

See all publications

Team Leader

Shirui Pan

Professor and ARC Future Fellow

Shirui Pan

Professor and ARC Future Fellow

PhD Students

Xin Zheng

PhD Students @ Monash (04/2021-)

Yixin Liu

PhD Student @ Monash (01/2021-)

Linhao Luo

PhD Student @ Monash (02/2022-)

Dongran Yu

PhD Student @ Jili (09/2019-)

He Zhang

PhD Student @ Monash (04/2021-)

Luzhi Wang

PhD Student @ Tianjin U. (07/2020-)

Yizhen Zheng

PhD Student @ Monash (07/2021-)

Bo Xiong

PhD Student @ Universität Stuttgart (09/2020-)

Yuanzhe Zhang

PhD Student @ Monash (06/2021-)

Ming Jin

PhD Student @ Monash (08/2020-)

Huan Yee Koh

PhD Student @ Monash (04/2022-)

Jiaxin Ju

PhD Student @ Griffith University (02/2023-)

Dongwon Ryu

PhD Student @ Monash (02/2021-)

Guangsi Shi

PhD Student @ Monash (07/2020-)

Mohit Gupta

PhD Student @ Monash (01/2022-)

Zahra Zamanzadeh

PhD Student @ Monash (01/2022)

Alumni

Miao Zhang

Professor @ Harbin Institute of Technology

Sheng Wan

PostDoc @ NUST

Bang Wu

Postdoc @ CSIRO’s Data61

Zonghan Wu

CEO

Shichao Zhu

AI Scientist @ ByteDance

Man Wu

Assistant Prof @ U. Sci&Tec Beijing

Hong Yang

Associate Professor @ Guangzhou University

Chun Wang

Assistant Professor @ City University of Macau

Ruiqi Hu

CEO

Shaoxiong Ji

Postdoc @ University of Helsinki

Guojia Wan

Postdoc @ Wuhan U.

Awards and Grants

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]: 2024 IEEE CIS TNNLS Outstanding Paper Award
[Award]: Fellow of Queensland Academy of Arts and Sciences (QAAS).
[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
- ARC Future Fellow
- Australian Research Council (ARC)
[Award]: 5 Papers are Selected as Most Influential Papers in IJCAI (02/2022).
- 2021 Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning, Ming Jin et al (Rank: 12)
- 2019 Graph WaveNet For Deep Spatial-Temporal Graph Modeling, Zonghan Wu et al (Rank: 1)
- 2019 Attributed Graph Clustering: A Deep Attentional Embedding Approach, Chun Wang et al (Rank: 9)
- 2018 Adversarially Regularized Graph Autoencoder For Graph Embedding, Shirui Pan et al (Rank: 4)
- 2016 Tri-Party Deep Network Representation, IJCAI-2016, Shirui Pan et al (Rank: 6)
[Award]: 1 Paper is Selected as Most Influential Paper in KDD (02/2022).
- 2020 Connecting The Dots: Multivariate Time Series Forecasting With Graph Neural Networks, Zonghan Wu et al (Rank: 4)
[Award]: 1 Paper is Selected as Most Influential Paper in AAAI (02/2022).
- 2018 DiSAN: Directional Self-Attention Network For RNN/CNN-Free Language Understanding, Tao Shen et al (Rank: 11)
[Award]: 1 Paper is Selected as Most Influential Paper in CIKM (02/2022).
- 2017 MGAE: Marginalized Graph Autoencoder For Graph Clustering, CIKM-2017, Chun Wang et al (Rank: 9)
[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
- Faculty Early Career Researcher Grant
- Monash University
Cyberbullying Detection on Social Networks ($20,000) - 2016-2017
- UTS Early Career Researcher Grant (UTS - ECRG)
- University of Technology Sydney

Professional Services

Editorship

Associate Editor: IEEE Transactions on Cybernetics (TCYB) (IF: 19.11)(2023-)
Associate Editor: Neural Networks (IF: 9.657)(2023-)
Associate Editor: Knowledge and Information Systems (IF: 2.531) (2022-)
Guest Editor for Special Issue: Pattern Recognition (2022)
Guest Editor for Special Issue: IEEE Transactions on Neural Networks and Learning Systems (2021)
Guest Editor for Special Issue: Future Generation Computer Systems (2020)
Guest Editor for Special Issue: Neurocomputing (2020)
Guest Editor for Special Issue: Complexity (2019)
Associate Editor: IEEE Access (2018-2019)

Conference Organisation

Proceeding Co-chair: 2022 IEEE International Conference on Data Mining(ADMA-2022)
Tutorial Chair: 2022 IEEE International Conference on Data Mining(ICDM-2022)
Program Chair: 2021 International Conference on Data Science and Systems (DSS-2021)
Workshop Chair: 2021 IEEE International Conference on Big Data (IEEE BigData-2021)
Tutorial Chair: 2020 Digital Image Computing: Techniques and Applications (DICTA-2020)
Special Session Chair: Learning from Big Graph Data: Theory and Applications, IJCNN-2018 (CORE A)
Special Session Chair: Advanced Data Analytics for Large-scale Complex Data Environment, IJCNN- 2017 (CORE A)
Special Session Chair: Advanced Machine Learning Methods and Applications from Complicated Data Environment, IJCNN-2016 (CORE A)

Journal Reviewer

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (CORE A*)
IEEE Transactions on Neural Networks and Learning Systems (TNNLS) (CORE A*)
IEEE Transactions on Knowledge and Data Engineering (TKDE)((CORE A*)
IEEE Transactions on Cybernetics (TCYB) (CORE A)
IEEE Transactions on Systems, Man and Cybernetics: Systems (SMCA) (CORE B)
IEEE Signal Processing Letters
ACM Transactions on Intelligent Systems and Technology (TIST)
World Wide Web (WWW) (CORE A)
Social Network Analysis and Mining
Neural Computing and Applications
Neurocomputing
Information Sciences (CORE A)

(Senior) Program Committee

The International Conference on Learning Representations (ICLR 23-21)
Annual Conference on Neural Information Processing Systems (NeurIPS 22-19) (CORE A*)
SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 22-19) (CORE A*)
Conference on Computer Vision and Pattern Recognition (CVPR 22-21) (CORE A*)
IEEE International Conference on Data Mining (ICDM 22-19) (CORE A*)
AAAI Conference on Artificial Intelligence (AAAI 23-17) (CORE A*)
The Web Conference (WWW 23-19) (CORE A*)
International Joint Conference on Artificial Intelligence (IJCAI 22-17) (CORE A*)
SIAM International Conference on Data Mining (SDM-19) (CORE A)
Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD-19,18,17,16)(CORE A)
IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2014-15)
International Conference on Advanced Data Mining and Applications (ADMA 2014, 2016)
The international conference on Advances in Social Network Analysis and Mining (ASONAM 2017)
The China Computer FedCOREtion (CCF) Conference on Big Data (CCF Big Data 2017)

Recent & Upcoming Talks

Towards Dynamic and Efficient Graph Neural Networks, Chinese Academy of Sciences , Beijing, China (Nov 8, 2019)
Learning from Graph Data: A Graph Neural Network Perspective, Beijing Institute of Technology , Beijing, China (Nov 7, 2019)
Towards Dynamic and Efficient Graph Neural Networks, CIKM-2019 Invited Talk, Beijing, China (Nov 7, 2019)
Learning from Graph Data: A Graph Neural Network Perspective, Monash University, Melbourne, Australia (Aug 7, 2019)

Source Codes

Curated List

A list of open source code is maintained on Github. Other source code will be released as it is ready for publishing.

Graph Classification

A number of graph datasets.

Teaching

FIT5196: Data Wrangling, Lecturer, 2019 S1, Monash University
FIT5196: Data Wrangling, Lecturer, 2020 S2, Monash University
FIT5196: Data Wrangling, Chief Examiner & Lecturer, 2021 S2, Monash University
FIT5212: Data Analysis for Semi-Structured Data, Co-Chief Examiner & Lecturer, 2020 S1, Monash University
FIT5212: Data Analysis for Semi-Structured Data, Co-Chief Examiner & Lecturer, 2021 S1, Monash University

Contact

s.pan@griffith.edu.au
+61 7 5678 0653
1 Parkland Dr, School of ICT, Griffith University,, Gold Coast, QLD 4125