Junquan Gu | 顾峻铨

Curriculum Vitae

Junquan Gu

Final-year Ph.D. student at Shanghai University. My work focuses on automated machine learning, automated feature engineering, graph learning, fraud detection, anomaly detection, and LLM-assisted machine learning systems.

gujunquan@shu.edu.cn Google Scholar GitHub ORCID

Education

Shanghai University

Ph.D. student, School of Computer Engineering and Science.

Research direction: AutoML, graph learning, fraud detection, anomaly detection, and LLM-assisted machine learning systems.

University of Queensland

Master's degree.

Queensland University of Technology

Bachelor's degree.

Profile

I work on machine learning methods for structured data, especially tabular and graph-structured data. My recent research studies how task semantics, feature construction, model selection, ensemble learning, and evaluation can be connected in automated learning pipelines for fraud detection and anomaly detection.

My first-author publications include work on dynamic incomplete graph anomaly detection, explainable anomaly detection, and open-source financial fraud data simulation.

Selected Publications

  1. Junquan Gu, Hang Yu, Xiangfeng Luo. A Masked AutoEncoder with Strong-Weak Mutual Information for Anomaly Detection in Dynamic Incomplete Graphs[C]. Companion Proceedings of the ACM on Web Conference 2025, 986-990.
  2. 骆祥峰, 顾峻铨, 余航. 基于强-弱互信息掩码学习的可解释动态不完整图异常检测[J]. 软件学报, 2026, 37(4): 1492-1510.
  3. Junquan Gu, Zehao Gong, Runchen Ji, Kun Shi, Xiangfeng Luo, Hang Yu. F2-Gen: An Open-Source Web Platform for Scenario-Driven Financial Fraud Data Simulation[C]. In Proceedings of the 49th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (Melbourne, Australia) (SIGIR ’26).

Full publication list →

Research Projects

  • Contributor to the National Key R&D Program project No. 2021YFC3300602 during doctoral study.
  • Contributor to NSFC-related research during doctoral study.

Academic Service

  • Reviewer for SIGIR, ICASSP, CAIS, and related academic venues.
  • Research mentoring and coordination for graduate students working on AutoML and anomaly detection.

Awards

  • Shanghai University “Challenge Cup” Excellent Project.
  • Shanghai University “Internet+” Gold Award.
  • 2022 “China Chuangyi” Entrepreneurship & Innovation Competition, Chongming Division, Merit Award.
  • Provincial First Prize, 17th “GigaDevice Cup” China Graduate Electronics Design Contest.

Technical Experience

  • Machine learning for tabular data and graph-structured data.
  • Automated feature generation, feature selection, model selection, and ensemble construction.
  • Experimental implementation and open-source release for fraud detection research.