About Me

Hi there! I am Yixin Liu, a research fellow at the Institute for Integrated and Intelligent Systems (IIIS), Griffith University, Australia, advised by Prof. Shirui Pan. Previous to that, I obtained my Ph.D. degree from the Faculty of Information Technology, Monash University, Australia in 2024, and obtained my B.S.&M.E. degree from Beihang University, China in 2017 and 2020, respectively. My research interests are in graph representation learning and graph neural networks, with a special focus on unsupervised and weak-supervised scenarios. I am a recipient of the Google Ph.D. Fellowship in 2022.

News

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

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