About me
I am a final year Ph.D student in Computer Science Department at UIUC under supervision of Prof. Jiawei Han. I received my Bachelor and Master degree in Computer Science at Zhejiang University and University of Illinois, respectively.
I am motivated to design graph learning algorithms that are robust to in-the-Wild distribution shifts in real-world applications. Specifically, I work on:
- Principles: transferable pre-training of GNNs (EGI), handling localized training data (SR-GNNs), domain adaptation via optimal Transport (GDOT)
- Applications: entity alignment on unknown types(CG-Align), name disambiguation in academia network (GAND)and etc.
Here is my resume. Free free to drop me an email for dicsussion (qiz3 AT illinois.edu).
Talks
Overcoming the Limitations of Localized Graph Training data
@ Graph Intelligence Sciences team at Microsoft MSAI, May 2022 Slides
Designing Robust Graph Neural Network against Distribution Shift
@ DGL Team, May 2022 Slides
Selected Publications
(*) indicates equal contributions
Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data Paper Code
Qi Zhu, Natalia Ponomareva, Jiawei Han, Bryan Perozzi
Proc. 2021 Conf. on Neural Information Processing Systems (NeurIPS’21)
Transfer learning of graph neural networks with ego-graph information maximization Paper
Qi Zhu*, Carl Yang*, Yidan Xu, Haonan Wang, Chao Zhang, Jiawei Han
Proc. 2021 Conf. on Neural Information Processing Systems (NeurIPS’21)
Collective Multi-type Entity Alignment Between Knowledge Graphs Paper Code Slides Media Coverage
Qi Zhu, Hao Wei, Bunyamin Sisman, Da Zheng, Christos Faloutsos, Xin Luna Dong, Jiawei Han
International World Wide Web Conference(WWW), 2020
Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks Paper Code
Yu Shi*, Qi Zhu*, Fang Guo, Chao Zhang, Jiawei Han (* equal contribution)
International Conference on Knowledge Discovery & Data Mining(KDD), 2018