About Me
HI! I am a researcher at Supcon working on Industrial AI. Our team is building a suite of industrial intelligent agents based on HGT fostering steady and sustainable business growth, including:
HR Agent Data Agent Sales Agent Biding Agent Meeting Agent Purchase Agent EfficiencyPi
My current work mainly focuses on using (hyper-)graph, ontology and large language models (LLMs) to encapsulate enterprise knowledge, business entities, and operational logic, enabling structured reasoning and task planning while preserving explainability and execution determinism. I am particularly interested in graph retrieval-augmented generation (GraphRAG) methods and graph foundation models, bridging the gap between cutting-edge AI research and real-world industrial applications.
Before joining Supcon, I received my Ph.D. from Tsinghua University in 2025, advised by Prof. Wei Xu, where I worked on fraud detection, multi-party computation, graph algorithms, and graph neural networks.
Please feel free to contact me! liuxin4@supcon.com; greenliuxin@163.com
Education
| Sep. 2019 - Dec. 2025 | Ph.D., Computer Science and Technology, Institute for Interdisciplinary Information Sciences, Tsinghua University |
| Sep. 2016 - Jun. 2019 | M.S., Computer Science and Technology, Institute for Interdisciplinary Information Sciences, Tsinghua University |
| Sep. 2012 - Jun. 2016 |
B.S., Statistics, School of Mathematical Sciences, Zhejiang University
Honor Degree, Advanced Honor Class of Engineering Education, Chu Kochen College |
Publications
-
Detecting LLM-Generated Spam Reviews by Integrating Language Model Embeddings and Graph Neural Network
Xin Liu*, Rongwu Xu*, Xinyi Jia, Jason Liao, Jiao Sun, Ling Huang, and Wei Xu. arXiv preprint, 2025
[paper] [bib]
-
Simplifying Root Cause Analysis in Kubernetes with StateGraph and LLM
Yong Xiang, Charley Peter Chen, Liyi Zeng, Wei Yin, Xin Liu, Hu Li, and Wei Xu. arXiv preprint, 2025
[paper] [bib]
-
Collaborative Fraud Detection on Large Scale Graph Using Secure Multi-Party Computation
Xin Liu, Xiaoyu Fan, Rong Ma, Kun Chen, Yi Li, Guosai Wang, and Wei Xu. CIKM 2024
[paper] [bib]
-
FDHelper: Assist Unsupervised Fraud Detection Experts with Interactive Feature Selection and Evaluation
Jiao Sun, Yin Li, Charley Chen, Jihae Lee, Xin Liu, Zhongping Zhang, Ling Huang, Lei Shi, and Wei Xu. CHI 2020
[bib]
-
No place to hide: Catching fraudulent entities in tensors
Yikun Ban, Xin Liu, Ling Huang, Yitao Duan, Xue Liu, and Wei Xu. WWW 2019
[paper] [bib] [poster]
-
FraudVis: Understanding Unsupervised Fraud Detection Algorithms
Jiao Sun, Qixin Zhu, Zhifei Liu, Xin Liu, Jihae Lee, Zhigang Su, Lei Shi, Ling Huang, and Wei Xu. PacificVis 2018
[bib]
-
Catching Loosely Synchronized Behavior in Face of Camouflage
Yikun Ban, Jiao Sun, Xin Liu, Ling Huang, Yitao Duan, and Wei Xu. arXiv preprint, 2018
[paper] [bib]
-
让AI读懂业务：本体论正在成为企业的“新智商”
Xin Liu. WeChat (in Chinese), 2025
[paper]
Research Experiences
| HGT Innovation Department, Supcon |
| Researcher, (2025 - 2026) |
| Enterprise Intelligence, Hypergraph, Graph Foundation Models, Large Language Models, Ontology |
| Institute for Interdisciplinary Information Sciences, Tsinghua University |
| PhD student (graduated), (Sep. 2016 - Dec. 2025) |
| Graph Algorithms, Multi-Party Computation, Graph Neural Networks, Fraud Detection |
Services
| 2024 | Session Chair - Privacy & Security Session, CIKM 2024 |