Liu Yang is an assistant professor in the Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences(CAS), ICT, CAS.

He got his PhD from Institute of Computing Technology Chinese Academy of Sciences under the supervision of Prof. Qing He, and co-supervised by Prof. Xiang Ao.

From Feb 2022 to Feb 2023, he was a visiting scholar in the NExT Research Centre, National University of Singapore(NUS), adviced by Prof. Chua Tat-Seng. Also, he worked with Prof. Fuli Feng and Prof. Yunshan Ma.

Previously, he received the B.S. degree in Mathematics from Nanjing University (NJU) in 2017.

My research interest includes graph machine learnig and AI safety. I have published 20+ papers at the top international AI conferences such as WWW, ICLR, KDD.

Our group welcomes visiting research intern students and feel free to reach out to me.

🔥 News

• 2026.01.11: 🎉 One paper is accepted by NeuraL Networks
• 2025.12.05: 🎉 One tutorial is accepted by WWW 2026
• 2025.08.31: 🎉 One tutorial is accepted by ICAIF 2025
• 2025.08.26: 🎉 One paper is accepted by ICDM 2025
• 2025.05.15: 🎉 One paper is accepted by KDD 2025
• 2025.01.25: 🎉 One paper is accepted by DASFFA 2025
• 2025.01.20: 🎉 Two papers are accepted by WWW 2025

📝 Selected Research Papers

🎙 Graph Machine Learning

• Neural Networks Graph-Agnostic Linear Transformers, Zhiyu Guo, Yang Liu, Xiang Ao, Yateng Tang, Xinhuan Chen, Xuehao Zheng, Qing He.
• KDD 2026 Live or Lie: Action-Aware Capsule Multiple Instance Learning for Risk Assessment in Live Streaming Platforms, Yiran Qiao, Jing Chen, Xiang Ao, Qiwei Zhong, Yang Liu, Qing He.
• ICAIF 2025 Robust Graph Learning in Finance, Xiang Ao, Yang Liu, Guansong Pang, Yuanhao Ding, Hezhe Qiao, Dawei Cheng, and Qing He.
• ICDM 2025 Dilution of Unreliable Information: Learning in Graph with Noisy Structures and Absent Attributes, Xinxin Li, Yang Liu, Weigao Wen, Siyong Xu, Qing He, and Xiang Ao.
• KDD 2025 GRASP: Differentially Private Graph Reconstruction Defense with Structured Perturbation, Zhiyu Guo, Yang Liu, Xiang Ao, Qing He.
• WWW 2025 SPEAR: A Structure-Preserving Manipulation Method for Graph Backdoor Attacks, Yuanhao Ding, Yang Liu, Yugang Ji, Weigao Wen, Qing He and Xiang Ao.
• WWW 2025 Panoramic Interests: Stylistic-Content Aware Personalized Headline Generation, Junhong Lian, Xiang Ao, Xinyu Liu, Yang Liu and Qing He.
• AAAI 2025 Dynamic Graph Learning with Static Relations for Credit Risk Assessment, Qi Yuan, Yang Liu, Yateng Tang, Xinhuan Chen, Xuehao Zheng, Qing He and Xiang Ao.
• DASFAA 2025 OFTEN: Graph Invariant Learning via Soft Environment Inference, Yang Liu, Zikun Zhang, Xiang Ao, Lingxiang Tian, Qing He.
• ICASSP 2025 Domain-aware Node Representation Learning for Graph Out-of-Distribution Generalization, Yi Qiao, Yang Liu, Qing He, Xiang Ao.
• WSDM 2025 LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework, Yiran Qiao, Xiang Ao, Yang Liu, Jiarong Xu, Xiaoqian Sun and Qing He.
• ICLR 2024 Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective, Kuan Li, Yiwen Chen, Yang Liu, Jin Wang, Qing He, Minhao Cheng and Xiang Ao.
• ICLR 2023 Revisiting Graph Adversarial Attack and Defense From a Data Distribution Perspective, Kuan Li, Yang Liu, Xiang Ao, Qing He.
• KDD 2023 FLOOD: A Flexible Invariant Learning Framework for Out-of-Distribution Generalization on Graphs, Yang Liu, Xiang Ao, Fuli Feng, Yunshan Ma, Kuan Li, Tat-Seng Chua and Qing He.
• KDD 2022 UD-GNN: Uncertainty-aware Debiased Training on Semi-Homophilous Graphs, Yang Liu, Xiang Ao, Fuli Feng, and Qing He.
• WWW 2021 Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection, Yang Liu, Xiang Ao, Zidi Qin, Jianfeng Chi, Jinghua Feng, Hao Yang and Qing He. Slides Talk
• CIKM 2020 Alike and Unlike: Resolving Class Imbalance Problem in Financial Credit Risk Assessment, Yang Liu, Xiang Ao, Qiwei Zhong, Jinghua Feng, Jiayu Tang, and Qing He. Slides Talk Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM), 2020.

–>

📖 Educations

• 2017.09 - 2023.06, PhD, Institute of Computing Technology Chinese Academy of Sciences, Beijing.
• 2022.02 - 2023.02, Visiting Student, National Univeristy of Singapore, Singapore.
• 2013.09 - 2017.06, Undergraduate, Nanjing University, Nanjing.

💻 Full List of Publications

🐍 2025

• Zhiyu Guo, Yang Liu, Xiang Ao and Qing He. GRASP: Differentially Private Graph Reconstruction Defense with Structured Perturbation. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 Pages 767-777 (KDD2025). https://doi.org/10.1145/3711896.3736992

• Yuanhao Ding, Yang Liu, Yugang Ji, Weigao Wen, Qing He, Xiang Ao. SPEAR: A Structure-Preserving Manipulation Method for Graph Backdoor Attacks. Proceedings of the ACM on Web Conference 2025, 1237 - 1247. https://doi.org/10.1145/3696410.3714665

• Junhong Lian, Xiang Ao, Xinyu Liu, Yang Liu and Qing He. Panoramic Interests: Stylistic-Content Aware Personalized Headline Generation. Companion Proceedings of the ACM on Web Conference 2025, Pages 1109 - 1112. https://doi.org/10.1145/3701716.3715539

• Qi Yuan, Yang Liu, Yateng Tang, Xinhuan Chen, Xuehao Zheng, Qing He, Xiang Ao. Dynamic Graph Learning with Static Relations for Credit Risk Assessment. Proceedings of the AAAI Conference on Artificial Intelligence, 39(12), 13133-13141, 2025. https://doi.org/10.1609/aaai.v39i12.33433

• Yang Liu, Zikun Zhang, Xiang Ao, Lingxiang Tian and Qing He. OFTEN: Graph Invariant Learning via Soft Environment Inference. In Proceedings of the 30th International Conference on Database Systems for Advanced Applications (DASFAA 2025).

• Xinxin Li, Yang Liu, Weigao Wen, Siyong Xu, Qing He, and Xiang Ao. Dilution of Unreliable Information: Learning in Graph with Noisy Structures and Absent Attributes. In Proceedings of the 25th IEEE International Conference on Data Mining (ICDM2025).

• Yiran Qiao, Xiang Ao, Yang Liu, Jiarong Xu, Xiaoqian Sun and Qing He. LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework. Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining, 232 - 241, 2025. https://doi.org/10.1145/3701551.3703488

• Yi Qiao, Yang Liu, Qing He and Xiang Ao. Domain-aware Node Representation Learning for Graph Out-of-Distribution Generalization. In Proceedings of 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2025).

🐎 2026

• Yiran Qiao, Jing Chen, Xiang Ao, Qiwei Zhong, Yang Liu, Qing He. Live or Lie: Action-Aware Capsule Multiple Instance Learning for Risk Assessment in Live Streaming Platforms. To appear in the 32nd SIGKDD Conference on Knowledge Discovery and Data Mining (KDD2026).

• Zhiyu Guo, Yang Liu, Xiang Ao, Yateng Tang, Xinhuan Chen, Xuehao Zheng, and Qing He. Graph-Agnostic Linear Transformers. To appear in Neural Networks.