AI4SE，具体为图表示学习、大语言模型等AI技术在软件工程上的应用

人工智能、软件工程

AI4SE，具体为图表示学习，智能体与大语言模型，及其在软件工程上的应用

   

博士就读于中国科学院大学软件工程专业，硕士就读于北京理工大学航空宇航科学与技术专业，本科就读于北京理工大学自动化专业

   

博士就读于中国科学院大学软件工程专业，硕士就读于北京理工大学航空宇航科学与技术专业，本科就读于北京理工大学自动化专业

个人成果包括一作/通讯发表CCF-A类论文7篇，并发表其他高水平论文20余篇，具体信息请见https://dblp.org/pid/16/6086-4.html

以一作、通讯发表CCF-A类论文8篇，共发表论文二十余篇，（CCF-A 10 篇、CCF-B 2 篇、CCF-C 5 篇、SCI 4 篇），主要方向为AI4SE，具体内容为图表示学习，大语言模型，及其在软件工程上的应用，谷歌学术主页：https://scholar.google.com/citations?user=gkK0P_kAAAAJ&hl=en, 主要发表信息如下：

1. 高航 (GAO H)​, 赵军锁 (ZHAO J S), 匡文渊 (KUANG W Y). 卫星互联网安全威胁分析与体系化防御策略 [J]. 中国科学：信息科学, 2026, 56(3): 620-642. DOI: 10.1360/SSI-2025-0491. (SCI，中科院二区；CCF-A-中文)​
2. GAO H*, PENG T*, CUI B Q, et al. Efficient code analysis via graph representation learning-guided large language models [C]//Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), Seoul, 2026 (Poster #65144). (CCF-A)​
3. GAO H*, ZHANG C H*, WANG T, et al. Learn to think: bootstrapping LLM logic through graph representation learning [C]//Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025). Freiburg: IJCAI Inc., 2025: 8058-8067. DOI: 10.24963/ijcai.2025/896. (CCF-A)​
4. GAO H*, HUANG W X*, WU F G, et al. LLM enhancers for GNNs: an analysis from the perspective of causal mechanism identification [C]//Proceedings of the 42nd International Conference on Machine Learning (ICML 2025). PMLR 267, 2025. (CCF-A)​
5. GAO H*, ZHANG C H*, WU F G, et al. Bootstrapping heterogeneous graph representation learning via large language models: a generalized approach [C]//Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI 2025). Menlo Park: AAAI Press, 2025: 16717-16726. DOI: 10.1609/aaai.v39i16.33837. (CCF-A)​
6. ZHANG C H, WU F G, GAO H. LNAHGN: LLM-guided neighbor aggregation for heterogeneous graph neural network [C]//Proceedings of the 32nd International Conference on Neural Information Processing (ICONIP 2025). Cham: Springer, 2025: 18-32. (CCF-C)​
7. HUANG W X, WU F G, GAO H, et al. Bootstrapping heterophily graph representation learning via a large language model-based approach [C]//Proceedings of the 37th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2025). Piscataway: IEEE, 2025: 122-129. DOI: 10.1109/ICTAI66417.2025.00024. (CCF-C)​
8. GAO H*, YAO C Y*, LI J M, et al. Rethinking causal relationships learning in graph neural networks [C]//Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024). Menlo Park: AAAI Press, 2024: 12145-12154. DOI: 10.1609/aaai.v38i11.29103. (CCF-A)​
9. LI J M, JIN Y F, GAO H, et al. Hierarchical topology isomorphism expertise embedded graph contrastive learning [C]//Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024). Menlo Park: AAAI Press, 2024. DOI: 10.1609/aaai.v38i12.29255. (CCF-A)​
10. WANG R, HOFGARD E F, GAO H, et al. Discovering symmetry breaking in physical systems with relaxed group convolution [C]//Proceedings of the 41st International Conference on Machine Learning (ICML 2024). PMLR 235, 2024. (CCF-A)​
11. GAO H, QIAO P, JIN Y F, et al. Introducing diminutive causal structure into graph representation learning [J]. Knowledge-Based Systems, 2024, 293: 111592. DOI: 10.1016/j.knosys.2024.111592. (SCI Q1，中科院一区)​
12. GUO Y Y, ZANG Z H, GAO H, et al. Unsupervised social event detection via hybrid graph contrastive learning and reinforced incremental clustering [J]. Knowledge-Based Systems, 2024, 284: 111225. DOI: 10.1016/j.knosys.2023.111225. (SCI Q1，中科院一区)​
13. YAO C Y, HUANG H, GAO H, et al. Molecular graph representation learning via structural similarity information [C]//Machine Learning and Knowledge Discovery in Databases: Research Track (ECML-PKDD 2024). Cham: Springer, 2024. DOI: 10.1007/978-3-031-70352-2_21. (CCF-B)​
14. YUAN J G, GAO H, WU F G, et al. Learning node representations under partial label learning [C]//Proceedings of the International Joint Conference on Neural Networks (IJCNN 2024). Piscataway: IEEE, 2024. DOI: 10.1109/IJCNN60899.2024.10651360. (CCF-C)​
15. GAO H*, LI J M*, QIANG W W, et al. Robust causal graph representation learning against confounding effects [C]//Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI 2023). Menlo Park: AAAI Press, 2023, 37(6): 7624-7632. DOI: 10.1609/aaai.v37i6.25925. (CCF-A)​
16. LI J M, GAO H, QIANG W W, et al. Information theory-guided heuristic progressive multi-view coding [J]. Neural Networks, 2023, 167: 415-432. DOI: 10.1016/j.neunet.2023.08.027. (SCI Q1，中科院一区)​
17. JIA D X, GAO H, SU X Z, et al. Introducing semantic-based receptive field into semantic segmentation via graph neural networks [C]//Neural Information Processing: Proceedings of the 30th International Conference (ICONIP 2023). Cham: Springer, 2023. DOI: 10.1007/978-981-99-8076-5_32. (CCF-C；ICONIP 2023 最佳论文提名)​
18. CHEN L P, JIA D X, GAO H, et al. SkaNet: split kernel attention network [C]//Artificial Neural Networks and Machine Learning (ICANN 2023). Cham: Springer, 2023. DOI: 10.1007/978-3-031-44192-9_37. (CCF-C)​
19. GAO H*, LI J M*, QIANG W W, et al. Bootstrapping informative graph augmentation via a meta learning approach [C]//Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI 2022). Freiburg: IJCAI Inc., 2022. DOI: 10.24963/ijcai.2022/416. (CCF-A)​
20. GAO H, LI J M, ZHENG C W. Self-supervised graph learning with segmented graph channels [C]//Machine Learning and Knowledge Discovery in Databases (ECML-PKDD 2022). Cham: Springer, 2022. DOI: 10.1007/978-3-031-26390-3_18. (CCF-B)​
21. GAO H, LI J M, QIAO P, et al. Weight-aware graph contrastive learning [C]//Artificial Neural Networks and Machine Learning (ICANN 2022). Cham: Springer, 2022: 719-730. DOI: 10.1007/978-3-031-15931-2_59. (CCF-C)