At present, I’m a master's student at Carnegie Mellon University, fortunately supervised by Prof. Kun Zhang. Previously, I received an M.Eng. degree from Tsinghua University in 2023, supervised by Prof. Yujiu Yang, and a B.M. degree from Sun Yat-sen University in 2020.
My research interest relies in graph representation learning (especially spectral graph neural networks), and causal discovery. Any ideas or discussions are more than welcomed all the time!
✉️ Email: [email protected]
[05/2023] Passed the final thesis defense of M.Eng., won Tsinghua Outstanding Master’s Thesis, and nominated as outstanding graduate student of Beijing city.
[04/2023] Three papers are accepted at ICML’23. Congrats to and thanks the insightful corporation work with Lin, Guangyi, Peng, Prof. Kun Zhang and Prof. Yujiu Yang!
[02/2023] Finished the research intern work at MBZUAI and got back to Shenzhen. Many thanks to the professors, researchers, students, and Tsinghua Alumni Associations in UAE. Such a great time there!
[09/2022] One paper got accepted at ICDMW’23, workshop of Learning on Graphs. Thanks the corporation with Lin!
[08/2022] Thanks the support of Prof. Kun, starting a half-year research intern at MBZUAI, Abu Dhabi.
… Not a good start for research - struggling in getting papers accepted and searching for deeper insight in graph representation learning, details are omitted …
Jiaqi Sun, Lin Zhang, Guangyi Chen, Kun Zhang, Peng Xu, Yujiu Yang. Feature Expansion for Graph Neural Networks. (ICML’23)
Xuanzhou Liu, Lin Zhang, Jiaqi Sun, Yujiu Yang, Haiqin Yang. D2Match: Leveraging Deep Learning and Degeneracy for Subgraph Matching. (ICML’23)
Peng XU, Lin Zhang, Xuanzhou Liu, Jiaqi Sun, Yue Zhao, Haiqin Yang, Bei Yu. Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks. (ICML’23)
Jiaqi Sun, Lin Zhang, Shenglin Zhao, Yujiu Yang. Improving Graph Neural Networks: A High-Frequency Booster. (MLoG Workshop of ICDM’22)
Junjie Wang*, Yatai Ji*, Jiaqi Sun, Yujiu Yang, and Tetsuya Sakai. 2021. MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering. (Findings of EMNLP’21)