我目前在山东大学软件学院攻读博士学位，师从孟雷教授。本人已于2022年6月从汕头大学工学院计算机系获得工程硕士学位；于2019年6月在河北科技大学理学院，信息与计算科学专业获得了理学学士学位。在学期间，围绕互联网大数据驱动下的多媒体计算和数据挖掘等科学问题开展研究，主要内容包括离群值检测算法研究以及多源信息融合的联邦学习算法研究。相关成果已在ACM MM、ECCV、ICME、TNNLS、IDAJ等国内外权威会议和期刊中发表。此外，我将于2024年12月以联合培养博士生身份前往新加坡南洋理工大学计算与数据科学学院Han Yu教授团队交流学习。 我的研究兴趣主要包括😎😎😎: ✔️ 联邦学习 (Federated Learning) ✔️ 分布外泛化 (Out-of-Distribution Generalization) ✔️ 异常值检测 (Outlier Detection)

📧 [E-mail] 🎓 [Google Scholar] 📥 [GitHub] 🆔 [ORCID] 📑 [English Page]

教育经历

• 2024.12 ~ 现在: 新加坡南洋理工大学, 计算机科学与工程学院, 访问博士 (CSC) [导师: 💁‍♂️Han Yu教授👍]

• 2022.09 ~ 现在: 山东大学, 软件学院, 在读博士 [导师: 💁‍♂️孟雷教授👍]

• 2019.09 ~ 2022.07: 汕头大学, 工学院计算机系, 硕士

• 2015.09 ~ 2019.07: 河北科技大学, 理学院, 学士

学术论文(*表示通讯作者)

2024

• Improving Global Generalization and Local Personalization for Federated Learning
  Lei Meng, Zhuang Qi*, Lei Wu, Xiaoyu Du, Zhaochuan Li, Lizhen Cui, Xiangxu Meng
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS'24), 2024.
  [中科院一区]
  

• Attentive Modeling and Distillation for Out-of-Distribution Generalization of Federated Learning
  Zhuang Qi, Weihao He, Xiangxu Meng, Lei Meng
  IEEE International Conference on Multimedia and Expo (ICME'24), 2024.
  [CCF B类会议]
  

• Cross-modal learning using privileged information for long-tailed image classification
  Xiangxian Li, Yuze Zheng, Haokai Ma, Zhuang Qi, Xiangxu Meng, Lei Meng
  Computational Visual Media (CVM'24), 2024.
  [中科院二区, CCF C类期刊]
  

• Cross-Training with Multi-View Knowledge Fusion for Heterogenous Federated Learning
  Zhuang Qi, Lei Meng, Weihao He, Ruohan Zhang, Yu Wang, Xin Qi, Xiangxu Meng
  Arxiv, 2024.
  

• Machine Learning Empowering Drug Discovery: Applications, Opportunities and Challenges
  Xin Qi, Yuanchun Zhao, Zhuang Qi, Siyu Hou, Jiajia Chen
  Molecules, 2024.
  [中科院二区]
  

• 基于跨模态特权信息增强的图像分类方法
  李象贤，郑裕泽，马浩凯，齐壮，闫晓硕，孟祥旭，孟雷
  软件学报, 2024.
  [CCF A类中文期刊]
  

2023

• Class-aware convolution and attentive aggregation for image classification
  Zitan Chen, Zhuang Qi, Xiangxian Li, Yuqing Wang, Lei Meng, Xiangxu Meng
  Proceedings of the 5th ACM International Conference on Multimedia in Asia (MM Asia'23), 2023.
  [CCF C类会议]
  

• Class-level Structural Relation Modeling and Smoothing for Visual Representation Learning
  Zitan Chen, Zhuang Qi, Xiao Cao, Xiangxian Li, Xiangxu Meng, Lei Meng
  Proceedings of the 31st ACM International Conference on Multimedia (MM'23), 2023.
  [CCF C类会议]
  

• Cross-silo prototypical calibration for federated learning with non-iid data
  Zhuang Qi, Lei Meng, Zitan Chen, Han Hu, Hui Lin, Xiangxu Meng
  Proceedings of the 31st ACM International Conference on Multimedia (MM'23), 2023.
  [CCF A类会议]
  

• Unsupervised Segmentation of Haze Regions as Hard Attention for Haze Classification
  Jingyu Li, Haokai Ma, Xiangxian Li, Zhuang Qi, Xiangxu Meng, Lei Meng
  International Conference on Image and Graphics (ICIG'23), 2023.
  [EI会议]
  

• Learning to fuse residual and conditional information for video compression and reconstruction
  Ran Wang, Zhuang Qi, Xiangxu Meng, Lei Meng
  International Conference on Image and Graphics (ICIG'23), 2023.
  [EI会议]
  

• Cross-Training with Prototypical Distillation for improving the generalization of Federated Learning
  Tianhan Liu, Zhuang Qi, Zitan Chen, Xiangxu Meng, Lei Meng
  2023 IEEE International Conference on Multimedia and Expo (ICME'23), 2023.
  [CCF B类会议]
  

• Cross-modal content inference and feature enrichment for cold-start recommendation
  Haokai Ma, Zhuang Qi, Xinxin Dong, Xiangxian Li, Yuze Zheng, Xiangxu Meng, Lei Meng
  2023 International Joint Conference on Neural Networks (IJCNN'23), 2023.
  [CCF C类会议]
  

• Multi-channel attentive weighting of visual frames for multimodal video classification
  Yuqing Wang, Zhuang Qi, Xiangxian Li, Jinxing Liu, Xiangxu Meng, Lei Meng
  2023 International Joint Conference on Neural Networks (IJCNN'23), 2023.
  [CCF C类会议]
  

2022

• Meta-causal feature learning for out-of-distribution generalization
  Yuqing Wang, Xiangxian Li, Zhuang Qi, Jingyu Li, Xuelong Li, Xiangxu Meng, Lei Meng
  European Conference on Computer Vision (ECCV'22), 2022.
  [CCF B类会议]
  

• Causal inference with sample balancing for out-of-distribution detection in visual classification
  Yuqing Wang, Xiangxian Li, Haokai Ma, Zhuang Qi, Xiangxu Meng, Lei Meng
  CAAI International Conference on Artificial Intelligence (CICAI'22), 2022.
  [CAAI A类会议]
  

• Clustering-based curriculum construction for sample-balanced federated learning
  Zhuang Qi, Yuqing Wang, Zitan Chen, Ran Wang, Xiangxu Meng, Lei Meng
  CAAI International Conference on Artificial Intelligence (CICAI'22), 2022.
  [CAAI A类会议]
  

• Prompt learning with cross-modal feature alignment for visual domain adaptation
  Jinxing Liu, Junjin Xiao, Haokai Ma, Xiangxian Li, Zhuang Qi, Xiangxu Meng, Lei Meng
  CAAI International Conference on Artificial Intelligence (CICAI'22), 2022.
  [CAAI A类会议]
  

• Unsupervised contrastive masking for visual haze classification
  Jingyu Li, Haokai Ma, Xiangxian Li, Zhuang Qi, Lei Meng, Xiangxu Meng
  Proceedings of the 2022 International Conference on Multimedia Retrieval (ICMR'22), 2022.
  [CCF B类会议]
  

• Robust Visual Tracking via Iterative Gradient Descent and Threshold Selectiong
  Zhuang Qi, Junlin Zhang, Xin Qi
  Arxiv, 2022.
  

• A novel density-based outlier detection method using key attributes
  Zhuang Qi, Xiaming Chen
  Intelligent Data Analysis Journal (IDA'22), 2022.
  [CCF C类期刊]
  

2021

• Iterative gradient descent for outlier detection
  Zhuang Qi, Dazhi Jiang, Xiaming Chen
  International Journal of Wavelets, Multiresolution and Information Processing (IJWMIP'21), 2021.
  [中科院四区]
  

• Relation Modeling and Distillation for Learning with Noisy Labels
  Zhuang Qi, Junlin Zhang, Xiaming Chen*, Xin Qi*
  Arxiv, 2021.
  

• Comparative Study of Neighbor-based Methods for Local Outlier Detection
  Zhuang Qi, Junlin Zhang, Xiaming Chen, Xin Qi
  Arxiv, 2021.
  

2020

• Hdiht: a high-accuracy distributed iterative hard thresholding algorithm for compressed sensing
  Xiaming Chen, Zhuang Qi, Jianlong Xu
  IEEE Access, 2020.
  [中科院二区]
  

荣誉奖励

• 河北科技大学2016-2017学年度校级模范学生干部 (2017.11)

• 2017年度国家励志奖学金 (2017.11)

• 河北科技大学2016-2017学年度校级三等奖学金 (2017.11)

• 2018年河北省大学生数学竞赛一等奖 (2018.12)

• 2018年全国大学生数学竞赛三等奖 (2018.12)

• 汕头大学2021年度硕士生一等学业奖学金 (2021.12)

• 2021年全国高等院校数学能力挑战赛决赛二等奖 (2021.12)

• 2022年首届IPv6技术应用创新大赛科教赛道暨第六届下一代互联网技术创新大赛中获得决赛优秀奖 (2022.12)

• 第十四届中国大学生服务外包创新创业大赛“合合信息杯”北部赛区赛，创新实践类，二等奖 (2023.06)

• 第十四届中国大学生服务外包创新创业大赛，创新实践类，三等奖 (2023.07)

• 第四届CCF大学生学术秀，博士组，三等奖 (2024.05)

• 2024年国家公派留学资格（CSC），联合培养博士生 (2024.07)

发明专利

• 基于原型引导交叉训练机制的联邦学习系统及方法
  孟雷, 齐壮, 刘天涵, 孟祥旭
  国家发明专利, 申请号: 2023103105396, 2023.3.23.

• 基于跨模态语义推理和融合的视觉感知推荐方法及系统
  孟雷, 马浩凯, 齐壮, 李象贤, 郑裕泽, 孟祥旭
  国家发明专利, 授权公告号: CN 114936901 B, 2024.05.28.

• 基于跨模态语义表征学习和融合的图像分类方法及系统
  孟雷, 李象贤, 郑裕泽, 马浩凯, 齐壮, 孟祥旭
  国家发明专利, 授权公告号: CN 114898156 B, 2024.06.04.

软件著作权

• 社会治理数字孪生实景三维系统
  著作权人：山东大学
  登记号：2023SR0716770.

• 社会治理多源数据处理
  著作权人：山东大学
  登记号：2023SR0887450.

学术服务

• The Annual AAAI Conference on Artificial Intelligence 2025 (AAAI'25), PC Member

• ACM International Conference on Multimedia 2024 (MM'24), 审稿人

• IEEE Conference on Computer Vision and Pattern Recognition 2024 (CVPR'24), 审稿人

• IEEE International Conference on Multimedia and Expo 2024 (ICME'24), 审稿人

• ACM International Conference on Multimedia 2023 (MM'23), 审稿人

• IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 审稿人, 2024.08-至今

• Computer Methods in Biomechanics and Biomedical Engineering, 审稿人, 2024.09-至今