About Me

Hi there! I am Yixin Liu, an ARC DECRA Fellow and Lecturer (Assistant Professor equivalent in the US system) at the School of Information and Communication Technology (ICT), Griffith University, Australia. Before taking up this role, I worked as a Research Fellow at Griffith University starting from 2024. I received my Ph.D. from the Faculty of Information Technology, Monash University, in 2024, and obtained my B.S. and M.E. degrees from Beihang University, China, in 2017 and 2020, respectively. My research interests lie in graph neural networks, large language models, agentic AI, and anomaly detection.

News

• 2026/01: Honored and excited to be appointed as a Lecturer (Assistant Professor equivalent) at Griffith University!
• 2025/12: Our survey on domain generalization/adaptation has been accepted by TPAMI.
• 2025/11: Honored and thrilled to receive ARC DECRA Fellowship 2026 (AU$496,368) for supporting my research on graph anomaly detection!
• 2025/11: Our paper on LLM multi-agent system design has been accepted by AAAI 2026.
• 2025/11: Our paper on graph anomaly detection has been accepted by AAAI 2026.
• 2025/10: Our position paper on graph-augmented LLM agents has been accepted by IEEE Intelligent Systems.
• 2025/09: Honored to be named in the list of the World’s Top 2% Scientists 2025 by Stanford University/Elsevier.
• 2025/09: Our survey on generalizable graph anomaly detection has been accepted by ICKG 2025.
• 2025/08: Our paper on LLM multi-agent system design has been accepted by EMNLP 2025.
• 2025/08: Our paper on graph anomaly detection has been accepted by CIKM 2025.
• 2025/06: Our paper on graph neural network has been accepted by TNNLS.
• 2025/02: Our paper on graph foundation model has been accepted by PAKDD 2025.
• 2025/01: Our benchmark on graph-level anomaly/OOD detection has been accepted by ICLR 2025.
• 2024/12: Our paper on graph fraud detection has been accepted by AAAI 2025.
• 2024/09: Our paper on generalist graph anomaly detection with in-context learning has been accepted by NeurIPS 2024.
• 2024/08: Our paper on data-efficient graph learning has been accepted by AI Magazine.
• 2024/07: Our paper on graph representation learning has been accepted by CIKM 2024.
• 2024/07: Our paper on data imputation has been accepted by CIKM 2024.
• 2024/05: Our paper on GNN against label noise has been accepted by KDD 2024.
• 2024/03: Our paper on diffusion model for data imputation has been accepted by ICLR 2024 GenAI4DM Workshop.
• 2024/02: Our survey on federated learning has been accepted by IJMLC.
• 2023/12: Our paper on graph OOD detection has been accepted by AAAI 2024.
• 2023/11: I give an invited talk at LoG Conference 2023 Shanghai meetup.
• 2023/11: Our paper on graph+LLM has been accepted by IEEE Intelligent Systems.
• 2023/09: Our paper on explainable graph anomaly detection has been accepted by NeurIPS 2023.
• 2023/09: Our survey on data-centric graph machine learning is now on arXiv.
• 2023/09: Our paper on graph anomaly detection has been accepted by ICDM 2023.
• 2023/06: We present a tutorial on graph self-supervised learning at IJCNN 2023.
• 2023/05: Our paper on weak information graph learning has been accepted by KDD 2023.
• 2022/11: Our paper on graph representation learning has been accepted by AAAI 2023.
• 2022/11: Our paper on federated graph learning has been accepted by AAAI 2023.
• 2022/10: Our paper on graph OOD detection has been accepted by WSDM 2023.
• 2022/08: I am honored to receive the Google Ph.D. Fellowship in 2022.
• 2022/05: Our survey on graph self-supervised learning has been accepted by IEEE TKDE.
• 2022/01: Our paper on graph structure learning has been accepted by WWW 2022.
• 2021/11: Our paper on dynamic graph has been accepted by IEEE TKDE.
• 2021/10: Our paper on graph anomaly detection has been accepted by IEEE TKDE.
• 2021/08: Our paper on graph anomaly detection has been accepted by CIKM 2021.
• 2021/06: Our paper on label propagation has been accepted by World Wide Web.
• 2021/03: Our paper on graph anomaly detection has been accepted by IEEE TNNLS.

Selected Papers (first-author/co-first-author)

Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark

Yili Wang*, Yixin Liu*, Xu Shen*, Chenyu Li*, Kaize Ding, Rui Miao, Ying Wang, Shirui Pan, Xin Wang

International Conference on Learning Representations (ICLR), 2025

[Paper] [Code]

ARC: A Generalist Graph Anomaly Detector with in-Context Learning

Yixin Liu, Shiyuan Li, Yu Zheng, Qingfeng Chen, Chengqi Zhang, Shirui Pan

Advances in Neural Information Processing Systems (NeurIPS), 2024

[Paper] [Code]

Self-supervision Improves Diffusion Models for Tabular Data Imputation

Yixin Liu, Thalaiyasingam Ajanthan, Hisham Husain, Vu Nguyen

ACM International Conference on Information & Knowledge Management (CIKM), 2024

[Paper] [Code]

Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation

Shiyuan Li*, Yixin Liu*, Qingfeng Chen, Geoffrey I Webb, Shirui Pan

ACM International Conference on Information & Knowledge Management (CIKM), 2024

[Paper] [Code]

Towards Self-Interpretable Graph-Level Anomaly Detection

Yixin Liu, Kaize Ding, Qinghua Lu, Fuyi Li, Leo Yu Zhang, Shirui Pan

Advances in Neural Information Processing Systems (NeurIPS), 2023

[Paper] [Code]

Learning Strong Graph Neural Networks with Weak Information

Yixin Liu, Kaize Ding, Jianling Wang, Vincent Lee, Huan Liu, Shirui Pan

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023

[Paper] [Code]

Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating

Yixin Liu, Yizhen Zheng, Daokun Zhang, Vincent Lee, Shirui Pan

AAAI Conference on Artificial Intelligence (AAAI), 2023 (Oral)

[Paper] [Code]

Federated Learning on Non-IID Graphs via Structural Knowledge Sharing

Yue Tan*, Yixin Liu*, Guodong Long, Jing Jiang, Qinghua Lu, Chengqi Zhang

AAAI Conference on Artificial Intelligence (AAAI), 2023 (Oral)

[Paper] [Code]

GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection

Yixin Liu, Kaize Ding, Huan Liu, Shirui Pan

ACM International Conference on Web Search and Data Mining (WSDM), 2023 (Oral)

[Paper] [Code]

Graph Self-Supervised Learning: A Survey

Yixin Liu, Ming Jin, Shirui Pan, Chuan Zhou, Yu Zheng, Feng Xia, Philip S. Yu

IEEE Transactions on Knowledge and Data Engineering (TKDE), 2022

[Paper]

Towards Unsupervised Deep Graph Structure Learning

Yixin Liu, Yu Zheng, Daokun Zhang, Hongxu Chen, Hao Peng, Shirui Pan

The Web Conference (WWW), 2022 (Best Paper Award candidate)

[Paper] [Code]

Anomaly Detection in Dynamic Graphs via Transformer

Yixin Liu, Shirui Pan, Yu Guang Wang, Fei Xiong, Liang Wang, Qingfeng Chen, Vincent Lee

IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021

[Paper] [Code]

Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning

Yixin Liu, Zhao Li, Shirui Pan, Chen Gong, Chuan Zhou, George Karypis

IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021

[Paper] [Code]

Education

• Ph.D. (2021-2024) in Monash University

• M.S. (2017-2020) in Beihang University

• B.S. (2013-2017) in Beihang University

Experience

• Griffith University, ARC Research Fellow, 2024-present.

• Amazon, Applied Scientist Intern, 2023.

• Monash University, Research Assistant, 2021.

• Alibaba, Research Intern, 2020.

Contact

• Email: yixin.liu[at]griffith[dot]edu[dot]au

• Office: G23 2.38, 1 Parkland Dr, Southport, QLD 4215