👋 About Me
I am currently a M.S. student at Central South University.
My research focuses on Graph Neural networks, Large Language Model, Data Mining, Graph Fraud detection, specifically the area of Large Language Models including their theoretical foundations and applications. I am looking for the academic internships any time and Ph.D. positions at Fall 2027. If you are interested in me, please feel free to email me at tairanhuang99@gmail.com.
🔥 News
- 2026.07: 🎉🎉 One paper is accepted by ACM MM 2026.
- 2026.02: 🎉🎉 One paper is accepted by CVPR 2026.
- 2025.11: 🎉🎉 One paper is accepted by AAAI 2026.
- 2025.10: 🎉🎉 One paper is accepted by NeurIPS 2025.
- 2025.07: 🎉🎉 One paper is accepted by ACM MM 2025.
📝 Selected Publications
UNIT: Unleash Large Language Models Potential for Graph Continual Learning
Tairan Huang, Yili Wang, Beibei Hu, Yiting Shi, Qiutong Li, Changlong He, Jianliang Gao
- Specific design for graph continual learning.
- Novel framework with uncertain-aware anchor generation and the structural confluence modeling.
ROVER: Robust Generative Continual Identity Unlearning against Relearning Attacks
Tairan Huang, Qiang Chen, Beibei Hu, Yunlong Zhao, Hongyan Xu, Zhiyuan Chen, Yi Chen, Xiu Su
- First exploration of robust multi-identity unlearning.
- Novel generative continual identity unlearning framework for unlearning multiple identities.
VL-Eraser: Vacuum Distillation for Machine Unlearning in Vision-Language Models
Yili Wang, Lu Dai, Tairan Huang, Yijie Xu, Hui Xiong.
- First analysis of machine unlearning paradigms in multimodal scenarios.
- Novel unlearning paradigm for Vision-language Models.
Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection
Tairan Huang, Yili Wang, Qiutong Li, Changlong He, Jianliang Gao
- First exploration of fraud detection with LLMs in graph.
- Novel multi-level LLM enhanced framework for graph fraud detection.
Simple and Efficient Heterogeneous Temporal Graph Neural Network
Yili Wang, Tairan Huang, Changlong He, Qiutong Li, Jianliang Gao
- Novel attention-based learning paradigm for HTGs.
- Novel dynamic attention mechanism with LLMs.
UNIT: Unleash Large Language Models Potential for Graph Continual Learning
ACM International Conference on Multimedia (ACM MM 2026)
VL-Eraser: Vacuum Distillation for Machine Unlearning in Vision-Language Models
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026)
ROVER: Robust Generative Continual Identity Unlearning against Relearning Attacks
AAAI Conference on Artificial Intelligence (AAAI 2026)
Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection
ACM International Conference on Multimedia (ACM MM 2025) (Oral)
Simple and Efficient Heterogeneous Temporal Graph Neural Network
Conference on Neural Information Processing Systems (NeurIPS 2025)
Lightning Decoupled Graph Neural Architecture Search for Fraud Detection
European Conference on Artificial Intelligence (ECAI 2025)
Multi-Faceted Consistency Data Augmentation for Graph Anomaly Detection
Information Processing & Management (IPM)
Revisiting Low-homophily for Graph-based Fraud Detection
Neural Networks
🎖 Honors and Awards
- 2025.10 National Scholarship, Ministry of Education of China. (Top 1%)
- 2024.10 Excellent Academic Scholarship of the Recommended Student, Central South University.
📖 Educations
- 2024.09 - 2027.06 (now), Master, Central South University, Changsha, China.
💬 Services
Reviewer:
- IEEE Transactions on Knowledge and Data Engineering (TKDE)
- AAAI Conference on Artificial Intelligence (AAAI 2026, 2027)