傅星珵 博士
职称：讲师/硕导
研究方向/教研室：计算机软件教研室
通信地址：广西桂林市七星区育才路15号广西师范大学计算机科学与工程学院
学术主页：https://fuxingcheng.github.io/
[个人简介][研究兴趣][工作经历][科研项目][代表性成果][主要教学工作]
傅星珵，男，壮族，籍贯广西河池宜州市，博士/讲师，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。主持国家自然科学基金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、入选广西第二批青苗人才计划。近五年在TPAMI、TKDE、ICML、NeurIPS、WWW、AAAI等CCF-A/B类国际权威学术期刊和顶级会议发表学术论文40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。获2022年北京市大数据与脑机智能高精尖创新中心卓越研究奖、2021年中国“互联网+”北京市一等奖、北航计算机学院抗疫突出贡献奖等；担任国际著名期刊TPAMI、IJCV、TKDE、TKDD、PR和国际顶级会议NeurIPS、ICLR、ICML、WWW、AAAI、KDD、ICDM审稿人，以及国际顶级会议ICML、ICLR、EMNLP区域主席（Area Chair）。
人工智能科学智算（AI for Science，AI4SCI）
人工智能教育系统（AI for Education，AI4EDU）
几何深度学习（双曲几何/黎曼几何学习）
低失真图表示学习
2024.11 - 至今 ：广西师范大学, 教育区块链与智能技术教育部重点实验室, 特聘研究员。
2023.10 - 至今 ：广西师范大学, 计算机科学与工程学院, 讲师。
2018.09 - 2023.06：北京航空航天大学, 计算机学院, 网络空间安全. 博士。
2015.09 - 2017.12：广西师范大学, 计算机科学与信息工程学院, 软件工程. 硕士。
2006.09 - 2010.06：解放军信息工程大学, 通信工程. 本科。
国家自然科学基金，地区科学基金项目，“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”，2025.01-2028.12，32万元，项目负责人，在研
教育区块链与智能技术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”，2025.01-2025.12, 8万元，项目负责人，在研
广西多源信息挖掘与安全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”，2025.01-2026.12，10万元，项目负责人，在研
科技部，科技创新2030 -“新一代人工智能”重大项目，“人工智能科学计算共性平台”，2023-03 至 2026-02，8800万元，参与，在研
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”，2021-12 至 2024-11，600万元，参与，结题
代表作论文
CCF-A: AAAI'26 Xingcheng Fu, Shengpeng Wang, Yisen Gao, Dongran Yu*, Chunpei Li, Qingyun Sun, Xianxian Li.Towards LLM-Empowered Knowledge Tracing via LLM-Student Hierarchical Behavior Alignment in Hyperbolic Space.
CCF-A: NeurIPS'25 Yisen Gao, Xingcheng Fu*(通讯作者), Qingyun Sun, Jianxin Li, Xianxian Li, Toward a Unified Geometry Understanding: Riemannian Diffusion Framework for Graph Generation and Prediction. [Paper][Video]
CCF-A: AAAI'25(Oral) Xingcheng Fu*, Yisen Gao, Beining Yang, Yuxuan Wu, Haodong Qian, Qingyun Sun, Xianxian Li. Bi-Directional Multi-Scale Graph Dataset Condensation via Information Bottleneck. [Paper][Video]
CCF-A: AAAI'25 Xingcheng Fu*, Jian Wang, Yisen Gao, Qingyun Sun*, Haonan Yuan, Jianxin Li, Xianxian Li. Discrete Curvature Graph Information Bottleneck. [Paper][Video]
CCF-A: ICML'24 Xingcheng Fu*, Yisen Gao, Yuecen Wei, Qingyun Sun, Hao Peng, Jianxin Li and Xianxian Li*. Hyperbolic Geometric Latent Diffusion Model for Graph Generation. International Conference on Machine Learning. [Paper][Slide][Video]
CCF-A: WWW'23(Spotlight焦点论文，全会16篇，网络和图领域唯一1篇) Xingcheng Fu, Yuecen Wei, Qingyun Sun, Haonan Yuan, Jia Wu, Hao Peng and Jianxin Li*. Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification. [Paper][Video]
CCF-B: KAIS'23(最佳论文候选邀请Track) Xingcheng Fu, Jianxin Li*, Jiawen Qin, Jia Wu, Qingyun Sun, Cheng Ji, Senzhang Wang, Hao Peng, Philip S. Yu. Adaptive Curvature Exploration Geometric Graph Neural Network.[Paper]
CCF-B: ICDM'21(最佳论文候选奖) Xingcheng Fu, Jianxin Li*, Jia Wu, Qingyun Sun, Cheng Ji, Senzhang Wang, Jiajun Tan, Hao Peng, Philip S. Yu. ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network.[Paper][Video]
CCF-A: IJCAI'25 Jinyan Wang, Liu Yang, Yuecen Wei, Jiaxuan Si, Chenhao Guo, Qingyun Sun, Xingcheng Fu(共同通讯作者), Xianxian Li. An Out-Of-Distribution Membership Inference Attack Approach for Cross-Domain Graph Attacks. [Paper]
CCF-A: IJCAI'25 Yudan Song, Yuecen Wei, Yuhang Lu, Qingyun Sun, Xingcheng Fu(共同通讯作者), Minglai Shao, Li-e Wang, Chunming Hu, Xianxian Li. Mitigating Message Imbalance in Fraud Detection with Dual-View Graph Representation Learning. [Paper]
CCF-A: AAAI'24 Yuecen Wei, Haonan Yuan, Xingcheng Fu*(共同通讯作者), Qingyun Sun, Hao Peng, Xianxian Li and Chunming Hu*. Poincaré Differential Privacy for Hierarchy-Aware Graph Embedding. [Paper]
CCF-A,SCI一区: TKDE'23 Jianxin Li*(博士生导师), Xingcheng Fu(学生一作), Hao Peng, Senzhang Wang, Shijie Zhu, Qingyun Sun, Philip S. Yu, Lifang He. A Robust and Generalized Framework for Adversarial Graph Embedding. [Paper]
CCF-A: WWW'22 Jianxin Li*(博士生导师), Xingcheng Fu(学生一作), Qingyun Sun, Cheng Ji, Jiajun Tan, Jia Wu, Hao Peng. Curvature Graph Generative Adversarial Networks. [Paper]
学术论文
·2026年
CCF-A,SCI一区: TPAMI'26 Qingyun Sun, Jiayi Luo, Haonan Yuan, Xingcheng Fu, Hao Peng, Jianxin Li and Philip S. Yu. Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environments.
CCF-A: KDD'26 Yuecen Wei, Liu Yang, Beining Yang, Qingyun Sun, Hao Peng, Tianyu Wo, Chunming Hu, Xingcheng Fu. Mitigating Privacy Risks in Graph Condensation from a Hyperbolic Geometry Perspective.
CCF-A: AAAI'26(Oral) Jiayi Luo, Qingyun Sun, Yuecen Wei, Haonan Yuan, Xingcheng Fu, Jianxin Li. Privacy Auditing of Multi-domain Graph Pre-trained Model under Membership Inference Attacks.
CCF-A: AAAI'26 Junhua Shi, Qingyun Sun, Haonan Yuan, Xingcheng Fu. SA²GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation.
CCF-A: AAAI'26(Oral) Yi Huang, Qingyun Sun, Yisen Gao, Haonan Yuan, Xingcheng Fu, Jianxin Li. Is the Information Bottleneck Robust Enough? Towards Label-Noise Resistant Information Bottleneck Learning.
CCF-A: AAAI'26 Jiayi Luo, Qingyun Sun, Lingjuan Lyu, Ziwei Zhang, Haonan Yuan, Xingcheng Fu, Jianxin Li. Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation Models.
·2025年
CCF-A: NeurIPS'25(Spotlight) Jiayi Luo, Qingyun Sun, Beining Yang, Haonan Yuan, Xingcheng Fu, Yanbiao Ma, Jianxin Li, Philip S. Yu. Robust Graph Condensation via Classification Complexity Mitigation.
CCF-A: NeurIPS'25 Haonan Yuan, Qingyun Sun, Junhua Shi, Xingcheng Fu, Bryan Hooi, Jianxin Li, Philip S. Yu. GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning.
CCF-A: NeurIPS'25 Zihao Guo, Qingyun Sun, Ziwei Zhang, Haonan Yuan, Huiping Zhuang, Xingcheng Fu, Jianxin Li. GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation.
CCF-A: IJCAI'25 Cheng Ji, Chenrui He, Qian Li, Qingyun Sun, Xingcheng Fu, Jianxin Li. OS-GCL: A One-Shot Learner in Graph Contrastive Learning.
CCF-A: IJCAI'25 Yumeng Wang, Zengyi Wo, Wenjun Wang, Xingcheng Fu, Minglai Shao. Leveraging Personalized PageRank and Higher-Order Topological Structures for Heterophily Mitigation in Graph Neural Networks.
CCF-A: ICML'25 Haonan Yuan, Qingyun Sun, Junhua Shi, Xingcheng Fu, Bryan Hooi, Jianxin Li, Philip S. Yu. How Much Can Transfer? BRIDGE: Bounded Multi-Domain Graph Foundation Model with Generalization Guarantees.
CCF-A: CVPR'25(Highlight, Top-13.5%) Tianyu Chen, Xingcheng Fu, Yisen Gao, Haodong Qian, Yuecen Wei, Kun Yan, Haoyi Zhou, Jianxin Li. Galaxy Walker: Geometry-aware VLMs For Galaxy-scale Understanding.
CCF-A: WWW'25 Beining Yang, Qingyun Sun, Cheng Ji, Xingcheng Fu, Jianxin Li. Robust Graph Learning Against Adversarial Evasion Attacks via Prior-Free Diffusion-Based Structure Purification.
CCF-A: ICLR'25 Jiawen Qin, Haonan Yuan, Qingyun Sun, Lyujin Xu, Jiaqi Yuan, Pengfeng Huang, Zhaonan Wang, Xingcheng Fu, Hao Peng, Jianxin Li, Philip S. Yu. IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning.
CCF-A: ICLR'25 Jiayi Luo, Qingyun Sun, Haonan Yuan, Xingcheng Fu, Jianxin Li. ST-GCond: Self-supervised and Transferable Graph Dataset Condensation.
CCF-A: AAAI'25 Yuecen Wei, Xingcheng Fu, Lingyun Liu, Qingyun Sun, HaoPeng, Chunming Hu*. Prompt-based Unifying Inference Attack on Graph Neural Networks.
CCF-A: AAAI'25 Zihao Guo, Qingyun Sun, Haonan Yuan, Xingcheng Fu, Min Zhou, Yisen Gao, Jianxin Li*. GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Experts.
CCF-A: AAAI'25 Haonan Yuan, Qingyun Sun, Zhaonan Wang, Xingcheng Fu, ChengJi, Yongjian Wang, Bo Jin, Jianxin Li*. DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models.
CCF-B: WSDM'25Jiawen Qin, Pengfeng Huang, Qingyun Sun, Cheng Ji, Xingcheng Fu, Jianxin Li. Graph Size-imbalanced Learning with Energy-guided Structural Smoothing.
·2024年以前
CCF-A: NeurIPS'24 Qingyun Sun, Ziying Chen, Beining Yang, Cheng Ji, Xingcheng Fu, Sheng Zhou, Hao Peng, Jianxin Li, Philip S. Yu. GC-Bench: An Open and Unified Benchmark for Graph Condensation.
CCF-A: WWW'24 Haonan Yuan, Qingyun Sun, Xingcheng Fu, Cheng Ji and Jianxin Li. Dynamic Graph Information Bottleneck.
CCF-A: AAAI'23 Qingyun Sun, Jianxin Li*, Beining Yang, Xingcheng Fu, Hao Peng, Philip S. Yu. Self-organization Preserved Graph Structure Learning with Principle of Relevant Information.
CCF-A: NeurIPS'23 Yuan, Haonan, Qingyun Sun*, Xingcheng Fu, Ziwei Zhang, Cheng Ji, Hao Peng and Jianxin Li. Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization.
CCF-A: NeurIPS'23 Yang, Beining, Kai Wang, Qingyun Sun*, Cheng Ji, Xingcheng Fu, Hao Tang, Yang You and Jianxin Li. Does Graph Distillation See Like Vision Dataset Counterpart?
CCF-A: AAAI'22 Qingyun Sun, Jianxin Li*, Hao Peng, Jia Wu, Xingcheng Fu, Cheng Ji, Philip S. Yu. Graph Structure Learning by Variational Information Bottleneck.
CCF-B: KAIS'24Yuecen Wei, Xingcheng Fu, Dongqi Yan, Qingyun Sun, Hao Peng, Jia Wu, Jinyan Wang*, Xianxian Li*. Heterogeneous graph neural network with semantic-aware differential privacy guarantees.
CCF-B,SCI一区: Information Sciences'23 Quanmin Wei, Jinyan Wang*, Xingcheng Fu, Jun Hu, Xianxian Li. AIC-GNN: Adversarial Information Completion for Graph Neural Networks.
CCF-B,SCI一区: Pattern Recognition'22 Cheng Ji, Tao Zhao, Qingyun Sun, Xingcheng Fu, Jianxin Li*. Higher-order Memory Guided Temporal Random Walk for Dynamic Heterogeneous Network Embedding.
CCF-B: WSDM'23 Cheng Ji, Jianxin Li*, Hao Peng, Jia Wu, Xingcheng Fu, Qingyun Sun, Philip S. Yu. Unbiased and Efficient Self-Supervised Incremental Contrastive Learning.
CCF-B: ECAI'23 Junnan Liu, Qianren Mao, Jianxin Li*, Xingcheng Fu, Zheng Wang. POINE2 : Improving Poincaré Embeddings for Hierarchy-Aware Complex Query Reasoning over Knowledge Graphs.
CCF-B: CIKM'22(最佳论文荣誉提名奖) Qingyun Sun, Jianxin Li*, Haonan Yuan, Xingcheng Fu, Hao Peng, Cheng Ji, Qian Li, Philip S. Yu. Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing. ACM International Conference on Information and Knowledge Management.
CCF-B: ICDM'22(最佳排名论文) Yuecen Wei, Xingcheng Fu, Qingyun Sun, Hao Peng, Jia Wu, Jinyan Wang*, Xianxian Li*. Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation.
奖励荣誉
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
可计算理论（研究生课程）
数据可视化技术（本科生课程）
人工智能通识（本科生课程）
算法设计与分析（本科生课程）