I am a Computer Science Ph.D candidate at University of Electronic Science and Technology of China (UESTC). I obtained my masterβs degree in Software Engineering at Guangxi Normal University (GXNU) in 2023 under the supervision of Prof.Xiaofeng Zhu. Before that, received my bachelorβs degree in Applied Statistics at Yulin Normal University in 2020.
My research interest includes few-shot learning, prompt learning, vision-language models and graph representation learning. I have published 5+ papers at the top international AI conferences such as AAAI, IJCAI, ACM Multimedia.
If you are interested in me, please contact wkzongqianwu@gmail.com.
π₯ News
- 2023.11: Β ππ One paper accepted by AAAI 2024!
- 2023.09: Β ββ Invited to serve as AAAI 2024 PC member.
- 2023.09: Β ββ I am going to UESTC in Chengdu to pursue a doctoral degree.
- 2023.08: Β ππ One paper accepted by ACM Multimedia 2023!
- 2023.06: Β ββ Defend my masterβs dissertation.
- 2023.06: Β ββ Invited to serve as ACM Multimedia 2023 PC member.
- 2023.04: Β ππ One paper accepted by IJCAI 2023!
π Publications
![sym](images/AMMPL.png)
Adaptive Multi-Modality Prompt Learning
πΒ Code
Zongqian Wu, Yujing Liu, Mengmeng Zhan, Jialie Shen, Ping Hu, Xiaofeng Zhu
- This paper introduces multi-modality prompt learning to address limitations in current methods, enhancing generalization by considering the impact of meaningless patches in images and simultaneously addressing in-sample and out-of-sample generalization.
![sym](images/KD-FSNC.png)
Self-training based Few-shot Node Classification by Knowledge Distillation
πΒ Code
Zongqian Wu, Yujie Mo, Peng Zhou, Shangbo Yuan, Xiaofeng Zhu
- This paper introduces a novel self-training FSNC method that addresses the limitations of existing approaches, leveraging representation and pseudo-label distillation techniques to enhance the utilization of base set information and mitigate the impact of low-quality pseudo-label.
![sym](images/IA-FSNC.png)
Information Augmentation for Few-shot Node Classifcation
πΒ Code
Zongqian Wu, Peng Zhou, Guoqiu Wen, Yingying Wan, Junbo Ma, Debo Cheng, Xiaofeng Zhu
- This paper proposes a new data augmentation method for few-shot node classification on graph data, mitigating issues with time costs and structural exploration. It involves efficient parameter initialization and fine-tuning with support and shot augmentation.
-
A Noise-resistant Graph Neural Network by Semi-supervised Contrastive Learning, Zhengyu Lu, Junbo Ma, Zongqian Wu, Bo Zhou, Xiaofeng Zhu, Information Science.
-
Multi-teacher Self-training for Semi-supervised Node Classification with Noisy Labels, Yujing Liu, Zongqian Wu, Zhengyu Lu, Guoqiu Wen, Junbo Ma, Guangquan Lu, Xiaofeng Zhu, ACM Multimedia 2023.
-
Totally Dynamic Hypergraph Neural Network, Peng Zhou, Zongqian Wu, Xiangxiang Zeng, Guoqiu Wen, Junbo Ma, Xiaofeng Zhu, IJCAI 2023.
-
Multiplex Graph Representation Learning via Common and Private Information Mining, Yujie Mo, Zongqian Wu, Yuhuan Chen, Xiaoshuang Shi, Heng Tao Shen, Xiaofeng Zhu, AAAI 2023.
-
Multi-scale Graph Classification with Shared Graph Neural Network, Peng Zhou, Zongqian Wu, Guoqiu Wen, Kun Tang, Junbo Ma, WWWJ
-
Mtgcn: A Multi-task Approach for Node Classification and Link Prediction in Graph Data, Zongqian Wu, Mengmeng Zhan, Haiqi Zhang, Qimin Luo, Kun Tang, Information Processing & Management.
π Honors and Awards
- 2023.06: Outstanding graduate of Guangxi Normal University.
- 2022.09: National scholarship (Top 1%).
- 2022.09: Academic star scholarship (10 students in the school each year).
π Educations
- 2023.09 - Present: UESTC
, Guiding Instructor: Prof.Xiaofeng Zhu, Team Instructors: Prof.Heng Tao Shen.
- 2020.09 - 2023.06: Guangxi Normal University
, Guiding Instructor: Prof.Xiaofeng Zhu, Team Instructors: Prof.Shichao Zhang.
- 2016.09 - 2020.06: Yulin Normal University
, Applied Statistics.
π¬ Invited Talks
- 2022.10: Information Augmentation for Few-shot Node Classification, IJCAI 2022 China, Shenzhen, China.
π Reviewer
- AAAI 2024
- IJCAI 2024
- ACM Multimedia 2023, 2024
- Neurocomputing
- IEEE Transactions on Image Processing
- IEEE Transactions on Knowledge and Data Engineering