个人简介

傅星珵，男，壮族，籍贯广西河池宜州市，博士/副教授，硕士研究生导师。2023年6月毕业于北京航空航天大学，获网络空间安全专业工学博士学位。主要研究方向为人工智能科学智算（AI4SCI）、人工智能教育系统（AI4EDU）、几何深度学习（Geometric Deep Learning）等。入选2025年度中国电子学会优博（全国34人）、广西第二批青苗人才计划，主持国家自然科学基金1项，省部级自然科学基金1项，教育部重点实验室/广西重点实验室开放课题2项，参与科技部重大项目2项。近五年在TPAMI、TKDE、ICML、NeurIPS、WWW、AAAI等国际权威学术期刊和顶级会议发表学术论文50余篇，获CCF-A类国际互联网技术顶级会议WWW 2023焦点论文-最佳论文提名奖(一作论文，全会16篇，网络和图领域唯一1篇)、国际数据挖掘顶级会议ICDM 2021最佳论文提名、ICDM 2022最佳排名论文、CIKM 2022最佳论文荣誉提名奖。担任国际顶级会议ICML、NeurIPS、ICLR、EMNLP领域主席（Area Chair）、国际著名期刊TPAMI、IJCV、TKDE、TKDD、PR和国际顶级会议NeurIPS、ICLR、ICML、WWW、AAAI、KDD、ICDM审稿人。

教育及工作经历

2023 - 至今

广西师范大学 · 计算机科学与工程学院/软件学院/人工智能学院

副教授、硕士生导师，教育部重点实验室特聘研究员

当前职位
2019 - 2023

北京航空航天大学 · 计算机学院 · 网络空间安全

工学博士

2014 - 2017

广西师范大学 · 计算机科学与信息工程学院 · 计算机科学与技术

工学硕士

2006 - 2010

解放军信息工程大学 · 信息工程学院 · 通信工程

本科

在研/参与项目

国家级主持

国家自然科学基金 · 地区基金

基于几何深度学习的社交网络关键结构可信挖掘方法研究，32万元。

省部级主持

广西壮族自治区 · “青苗人才计划”项目

基于几何深度学习的层次化知识教学行为研究，30万元。

省部级主持

广西自然科学基金 · 面上项目

学生行为和知识结构层次化精准感知的多模态教育大模型研究，10万元。

开放课题主持

教育部重点实验室系统性研究课题

层次化知识追踪和可解释多模态大模型教育辅导研究，8万元。

开放课题主持

广西重点实验室系统性研究课题

基于图几何学习的社交网络恶意检测，10万元。

国家级参与

科技部 · 科技创新2030—“新一代人工智能”重大项目

科技创新2030—“新一代人工智能”重大项目，8800万元。

国家级参与

科技部 · 科技创新2030—“新一代人工智能”重大项目

公共卫生事件的关联识别与追踪溯源方法，600万元。

学术成果

代表作论文

CCF-A
WWW'26Graph Diffusion Evolution Model for Multi-Conditional Molecular Generation.
Xingcheng Fu, Lingyun Liu, Yisen Gao, Tianyu Chen, Qingyun Sun*, Jianxin Li, Xianxian Li.
CCF-A
AAAI'26Towards LLM-Empowered Knowledge Tracing via LLM-Student Hierarchical Behavior Alignment in Hyperbolic Space.
Xingcheng Fu, Shengpeng Wang, Yisen Gao, Dongran Yu*, Chunpei Li, Qingyun Sun, Xianxian Li.
CCF-A
NeurIPS'25Toward a Unified Geometry Understanding: Riemannian Diffusion Framework for Graph Generation and Prediction.
Yisen Gao, Xingcheng Fu* (通讯), Qingyun Sun, Jianxin Li, Xianxian Li.
CCF-A
AAAI'25 (Oral)Bi-Directional Multi-Scale Graph Dataset Condensation via Information Bottleneck.
Xingcheng Fu*, Yisen Gao, Beining Yang, Yuxuan Wu, Haodong Qian, Qingyun Sun, Xianxian Li.
CCF-A
AAAI'25Discrete Curvature Graph Information Bottleneck.
Xingcheng Fu*, Jian Wang, Yisen Gao, Qingyun Sun*, Haonan Yuan, Jianxin Li, Xianxian Li.
CCF-A
ICML'24Hyperbolic Geometric Latent Diffusion Model for Graph Generation.
Xingcheng Fu*, Yisen Gao, Yuecen Wei, Qingyun Sun, Hao Peng, Jianxin Li and Xianxian Li*.
CCF-A
WWW'23 (Spotlight 焦点论文，最佳论文提名)Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification.
Xingcheng Fu, Yuecen Wei, Qingyun Sun, Haonan Yuan, Jia Wu, Hao Peng and Jianxin Li*.
CCF-B
KAIS'23 (最佳论文邀请Track)Adaptive Curvature Exploration Geometric Graph Neural Network.
Xingcheng Fu, Jianxin Li*, Jiawen Qin, Jia Wu, Qingyun Sun, Cheng Ji, Senzhang Wang, Hao Peng, Philip S. Yu.
CCF-B
ICDM'21 (最佳论文候选)ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network.
Xingcheng Fu, Jianxin Li*, Jia Wu, Qingyun Sun, Cheng Ji, Senzhang Wang, Jiajun Tan, Hao Peng, Philip S. Yu.
CCF-A
IJCAI'25An Out-Of-Distribution Membership Inference Attack Approach for Cross-Domain Graph Attacks.
Jinyan Wang, Liu Yang, Yuecen Wei, Jiaxuan Si, Chenhao Guo, Qingyun Sun, Xingcheng Fu (共同通讯), Xianxian Li.
CCF-A
IJCAI'25Mitigating Message Imbalance in Fraud Detection with Dual-View Graph Representation Learning.
Yudan Song, Yuecen Wei, Yuhang Lu, Qingyun Sun, Xingcheng Fu (共同通讯), Minglai Shao, Li-e Wang, Chunming Hu, Xianxian Li.
CCF-A
AAAI'24Poincaré Differential Privacy for Hierarchy-Aware Graph Embedding.
Yuecen Wei, Haonan Yuan, Xingcheng Fu* (共同通讯), Qingyun Sun, Hao Peng, Xianxian Li and Chunming Hu*.
CCF-ASCI一区
TKDE'23A Robust and Generalized Framework for Adversarial Graph Embedding.
Jianxin Li* (博导), Xingcheng Fu (学生一作), Hao Peng, Senzhang Wang, Shijie Zhu, Qingyun Sun, Philip S. Yu, Lifang He.
CCF-A
WWW'22Curvature Graph Generative Adversarial Networks.
Jianxin Li* (博导), Xingcheng Fu (学生一作), Qingyun Sun, Cheng Ji, Jiajun Tan, Jia Wu, Hao Peng.

学术论文

2026年
CCF-ASCI一区
TPAMI'26Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environments.
Qingyun Sun, Jiayi Luo, Haonan Yuan, Xingcheng Fu, Hao Peng, Jianxin Li, Philip S. Yu.
CCF-CSCI一区
KBS'26Rethinking heterophilic graph learning via graph curvature.
Jian Wang, Xingcheng Fu, Qingyun Sun, Li-E Wang, Hao Peng, Jiting Li*, Xianxian Li, Minglai Shao.
CCF-A
ICLR'26Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs.
Yisen Gao, Jiaxin Bai, Tianshi Zheng, Ziwei Zhang, Qingyun Sun, Xingcheng Fu, Jianxin Li, Yangqiu Song.
CCF-A
WWW'26Towards Geometry-Consistent Federated Graph Learning.
Yuecen Wei, Zhiyu Zhuang, Yisen Gao, Xingcheng Fu, Qingyun Sun, Ziwei Zhang, Tianyu Wo and Chunming Hu.
CCF-A
KDD'26Mitigating Privacy Risks in Graph Condensation from a Hyperbolic Geometry Perspective.
Yuecen Wei, Liu Yang, Beining Yang, Qingyun Sun, Hao Peng, Tianyu Wo, Chunming Hu, Xingcheng Fu.
CCF-A
AAAI'26 (Oral)Privacy Auditing of Multi-domain Graph Pre-trained Model under Membership Inference Attacks.
Jiayi Luo, Qingyun Sun, Yuecen Wei, Haonan Yuan, Xingcheng Fu, Jianxin Li.
CCF-A
AAAI'26SA²GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation.
Junhua Shi, Qingyun Sun, Haonan Yuan, Xingcheng Fu.
CCF-A
AAAI'26 (Oral)Is the Information Bottleneck Robust Enough? Towards Label-Noise Resistant Information Bottleneck Learning.
Yi Huang, Qingyun Sun, Yisen Gao, Haonan Yuan, Xingcheng Fu, Jianxin Li.
CCF-A
AAAI'26Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation Models.
Jiayi Luo, Qingyun Sun, Lingjuan Lyu, Ziwei Zhang, Haonan Yuan, Xingcheng Fu, Jianxin Li.
2025年
CCF-A
NeurIPS'25 (Spotlight)Robust Graph Condensation via Classification Complexity Mitigation.
Jiayi Luo, Qingyun Sun, Beining Yang, Haonan Yuan, Xingcheng Fu, Yanbiao Ma, Jianxin Li, Philip S. Yu.
CCF-A
NeurIPS'25GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning.
Haonan Yuan, Qingyun Sun, Junhua Shi, Xingcheng Fu, Bryan Hooi, Jianxin Li, Philip S. Yu.
CCF-A
NeurIPS'25GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation.
Zihao Guo, Qingyun Sun, Ziwei Zhang, Haonan Yuan, Huiping Zhuang, Xingcheng Fu, Jianxin Li.
CCF-A
IJCAI'25OS-GCL: A One-Shot Learner in Graph Contrastive Learning.
Cheng Ji, Chenrui He, Qian Li, Qingyun Sun, Xingcheng Fu, Jianxin Li.
CCF-A
IJCAI'25Leveraging Personalized PageRank and Higher-Order Topological Structures for Heterophily Mitigation in Graph Neural Networks.
Yumeng Wang, Zengyi Wo, Wenjun Wang, Xingcheng Fu, Minglai Shao.
CCF-A
ICML'25How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Foundation Model with Generalization Guarantees.
Haonan Yuan, Qingyun Sun, Junhua Shi, Xingcheng Fu, Bryan Hooi, Jianxin Li, Philip S. Yu.
CCF-A
CVPR'25 (Highlight, Top-13.5%)Galaxy Walker: Geometry-aware VLMs For Galaxy-scale Understanding.
Tianyu Chen, Xingcheng Fu, Yisen Gao, Haodong Qian, Yuecen Wei, Kun Yan, Haoyi Zhou, Jianxin Li.
CCF-A
WWW'25Robust Graph Learning Against Adversarial Evasion Attacks via Prior-Free Diffusion-Based Structure Purification.
Beining Yang, Qingyun Sun, Cheng Ji, Xingcheng Fu, Jianxin Li.
CCF-A
ICLR'25 (Spotlight)IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning.
Jiawen Qin, Haonan Yuan, Qingyun Sun, Lyujin Xu, Jiaqi Yuan, Pengfeng Huang, Zhaonan Wang, Xingcheng Fu, Hao Peng, Jianxin Li, Philip S. Yu.
CCF-A
ICLR'25ST-GCond: Self-supervised and Transferable Graph Dataset Condensation.
Jiayi Luo, Qingyun Sun, Haonan Yuan, Xingcheng Fu, Jianxin Li.
CCF-A
AAAI'25Prompt-based Unifying Inference Attack on Graph Neural Networks.
Yuecen Wei, Xingcheng Fu, Lingyun Liu, Qingyun Sun, Hao Peng, Chunming Hu*.
CCF-A
AAAI'25GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Experts.
Zihao Guo, Qingyun Sun, Haonan Yuan, Xingcheng Fu, Min Zhou, Yisen Gao, Jianxin Li*.
CCF-A
AAAI'25DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models.
Haonan Yuan, Qingyun Sun, Zhaonan Wang, Xingcheng Fu, Cheng Ji, Yongjian Wang, Bo Jin, Jianxin Li*.
CCF-B
WSDM'25Graph Size-imbalanced Learning with Energy-guided Structural Smoothing.
Jiawen Qin, Pengfeng Huang, Qingyun Sun, Cheng Ji, Xingcheng Fu, Jianxin Li.
2024年及以前
CCF-A
NeurIPS'24GC-Bench: An Open and Unified Benchmark for Graph Condensation.
Qingyun Sun, Ziying Chen, Beining Yang, Cheng Ji, Xingcheng Fu, Sheng Zhou, Hao Peng, Jianxin Li, Philip S. Yu.
CCF-A
WWW'24Dynamic Graph Information Bottleneck.
Haonan Yuan, Qingyun Sun, Xingcheng Fu, Cheng Ji and Jianxin Li.
CCF-A
AAAI'23Self-organization Preserved Graph Structure Learning with Principle of Relevant Information.
Qingyun Sun, Jianxin Li*, Beining Yang, Xingcheng Fu, Hao Peng, Philip S. Yu.
CCF-A
NeurIPS'23Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization.
Yuan, Haonan, Qingyun Sun*, Xingcheng Fu, Ziwei Zhang, Cheng Ji, Hao Peng and Jianxin Li.
CCF-A
NeurIPS'23Does Graph Distillation See Like Vision Dataset Counterpart?
Yang, Beining, Kai Wang, Qingyun Sun*, Cheng Ji, Xingcheng Fu, Hao Tang, Yang You and Jianxin Li.
CCF-A
AAAI'22Graph Structure Learning by Variational Information Bottleneck.
Qingyun Sun, Jianxin Li*, Hao Peng, Jia Wu, Xingcheng Fu, Cheng Ji, Philip S. Yu.
CCF-B
KAIS'24Heterogeneous graph neural network with semantic-aware differential privacy guarantees.
Yuecen Wei, Xingcheng Fu, Dongqi Yan, Qingyun Sun, Hao Peng, Jia Wu, Jinyan Wang*, Xianxian Li*.
CCF-BSCI一区
Information Sciences'23AIC-GNN: Adversarial Information Completion for Graph Neural Networks.
Quanmin Wei, Jinyan Wang*, Xingcheng Fu, Jun Hu, Xianxian Li.
CCF-BSCI一区
Pattern Recognition'22Higher-order Memory Guided Temporal Random Walk for Dynamic Heterogeneous Network Embedding.
Cheng Ji, Tao Zhao, Qingyun Sun, Xingcheng Fu, Jianxin Li*.
CCF-B
WSDM'23Unbiased and Efficient Self-Supervised Incremental Contrastive Learning.
Cheng Ji, Jianxin Li*, Hao Peng, Jia Wu, Xingcheng Fu, Qingyun Sun, Philip S. Yu.
CCF-B
ECAI'23POINE2 : Improving Poincaré Embeddings for Hierarchy-Aware Complex Query Reasoning over Knowledge Graphs.
Junnan Liu, Qianren Mao, Jianxin Li*, Xingcheng Fu, Zheng Wang.
CCF-B
CIKM'22 (最佳论文荣誉提名)Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing.
Qingyun Sun, Jianxin Li*, Haonan Yuan, Xingcheng Fu, Hao Peng, Cheng Ji, Qian Li, Philip S. Yu.
CCF-B
ICDM'22 (最佳排名论文)Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation.
Yuecen Wei, Xingcheng Fu, Qingyun Sun, Hao Peng, Jia Wu, Jinyan Wang*, Xianxian Li*.

荣誉奖励

  • 2026.03 2025年度中国电子学会博士学位论文激励计划（中国电子学会优博，全国34人）

  • 2023.06 北京航空航天大学优秀毕业生

  • 2022.06 北京航空航天大学优秀学术创新成果奖

  • 2022.03 北京航空航天大学计算机学院研究生“创新奖”(团队)

  • 2022.01 北京市大数据与脑机智能高精尖创新中心卓越研究奖

  • 2021.08 中国“互联网 +”大学生创新创业大赛北京市一等奖

  • 2021.01 北京航空航天大学“优秀研究生”

  • 2020.09 北航计算机学院抗疫突出贡献奖

  • 2020.05 国务院办公厅感谢函，《科技日报》头版报道

MAGIC-GXNU  图智能计算组

MAGIC图智能计算组由北航ACT实验室-广西师大教育部重点实验室联合组建，由傅星珵副教授、孙庆赟副教授（北航）、张子威副教授（北航）联合指导，现有博士/硕士研究生及本科实习生10余人，研究氛围活跃，成果丰硕。

在读博士/硕士（部分）

韦岳岑
博士三年级 · 北京航空航天大学
图隐私模型 | CCF-A类4篇、B类2篇
王盛鹏
硕士二年级
知识追踪与教育大模型 | CCF-A会议1篇，CCF-A/SCI一区在投各1篇
刘凌云
硕士二年级
双曲几何与分子结构生成 | CCF-A会议1篇，CCF-A/SCI一区期刊在投2篇
黄字嘉
硕士一年级
图基础模型和智能体记忆
刘思彤
硕士一年级
图智能体异常检测
李志强
硕士一年级
零样本学习与智能体

学术活动

会议
WWW 2024 新加坡 · 圣淘沙岛参会
交流
ICML 2024 奥地利 · 维也纳参会
交流
AAAI 2025 美国 · 费城参会
交流
ICLR 2025 新加坡 · EXPO参会
交流
AAAI 2026 新加坡 · EXPO参会
报告
IJCAI 2025 Tutorial报告 蒙特利尔|广州
团建
学术酒吧 桂林 · 王城

加入MAGIC课题组

欢迎对图学习、几何深度学习、AI4Science/AI4Education感兴趣的同学报考硕士研究生，或申请本科实习生。

基本要求：扎实的编程与数学基础，英语良好，与团队文化Active(自驱力)、Creative(好奇心)、Teamwork(团队协作)matching的同学。

联系邮箱：fuxc@gxnu.edu.cn（邮件标题：[硕士/本科实习生申请]姓名-学校-专业）

2026年秋季研究生招生已结束，欢迎本科生申请实习，提供充足算力、全额资助参加国内外顶级会议。

历届研究生去向（部分）

姓名毕业年份类别去向单位岗位/学位
宋雨丹2025国企/事业单位某烟草系统公务员
陶仕儇2025机关单位某税务系统公务员
王坚2026学术深造中南大学攻读博士
杨柳2026学术深造华东师范大学攻读博士
陆宇航2026学术深造南京理工大学攻读博士