Basic Information

 

邓辉琦 Huiqi Deng

博士 助理教授
西安交通大学计算机科学与技术学院
智能网络与网络安全教育部重点实验室

denghq7@xjtu.edu.cn

Google Scholar

 

Honors

  • 西安交通大学“青年优秀人才支持计划”，2024
  • 国家资助博士后研究人员计划 B 档，2024（导师：管晓宏教授）
  • 上海市超级博士后激励计划，2022
  • 全国博士后创新创业大赛优胜奖，2021

站点计数器

News

Research Background

研究兴趣：（i）可解释与可信人工智能（Explainable and Trustworthy AI）：致力于揭示神经网络的黑盒决策过程及其内在机理，进而对模型的安全性和可靠性进行系统评估、调控与优化，最终构建可解释、安全可控的人工智能系统。应用场景包含计算机视觉、自然语言处理、图数据挖掘等；(ii) 大模型交叉应用（LLM applications）：通过人工智能技术（尤其是大模型），推动跨学科研究范式的革新。典型应用包括：AI赋能的网络配置优化（AI for network configuration）、AI驱动的药物发现（AI for drug discovery）等。
 

工作及学习经历：

  • 2024 - 至今，西安交通大学 计算机科学与技术学院，助理教授
  • 2022 - 2024，上海交通大学电子信息与电气工程学院，博士后
  • 2015 - 2021，中山大学数学学院，硕博连读
  • 2019 - 2020，德州农工大学计算机系（TAMU），访问学生
  • 2017 - 2019，香港浸会大学计算机系（HKBU），研究助理


学术服务：

  • 担任期刊审稿人： IEEE TPAMI, IEEE TKDE, IEEE TNNLS等
  • 担任会议程序委员会成员/审稿人： ICML, NeurIPS, ICLR, AAAI, IJCAI, CVPR 等

 

长期招收硕士、本科生：如果你对可信人工智能、计算机视觉、自然语言处理、图数据挖掘、及AI 交叉应用等领域感兴趣，有较强的学习能力、自我驱动力，且编程/数学能力突出，欢迎联系我们。Email: denghq7 at xjtu.edu.cn

Selected Publications

（* 代表 equal contribution）
 

         可解释、可信人工智能方向：

  1. Huiqi Deng, Na Zou, Mengnan Du, Weifu Chen, Guocan Feng, Ziwei Yang, Zheyang Li, Quanshi Zhang. Unifying Fourteen Post-Hoc Attribution Methods With Taylor Interactions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024 (IEEE TPAMI；CCF-A类期刊；IF = 20.8，详见知乎介绍：论统一14种输入重要性归因算法)

  2. Huiqi Deng*, Qihan Ren*, Hao Zhang, Quanshi Zhang. Discovering and Explaining the Representation Bottleneck of DNNs. International Conference on Learning Representations, 2022 (ICLR Oral Paper 录用率1.6%；清华 A 类会议；详见知乎介绍：神经网络的知识表达瓶颈)

  3. Dongrui Liu*, Huiqi Deng*, Xu Cheng, Qihan Ren, Kangrui Wang, Quanshi Zhang. Towards the difficulty for a deep neural network to learn concepts of different complexities. Conference and Workshop onNeural Information Processing Systems, 2023 (NeurIPS；CCF-A 类会议）

  4. Qihan Ren*, Huiqi Deng*, Yunuo Chen, Siyu Lou, Quanshi Zhang. Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts. International Conference on Machine Learning, 2023（ ICML; CCF-A类会议）

  5. Huiqi Deng, Na Zou, Mengnan Du, Weifu Chen, Guocan Feng, Xia Hu. A Unified Taylor Framework for Revisiting Attribution Methods. AAAI Conference on Artificial Intelligence, 2021（AAAI; CCF-A类会议）

  6. Huiqi Deng, Na Zou, Weifu Chen, Guocan Feng, Mengnan Du, Xia Hu. Mutual Information Preserving Back-propagation: Learn to Invert for Faithful Attribution. ACM SIGKDD Conference on Knowledge Discovery and Data Mining （KDD; CCF-A类会议）

  7. Huiqi Deng, Weifu Chen, Qi Shen, Andy J. Ma, Pong C. Yuen, Guocan Feng. Invariant subspace learning for time series data based on dynamic time warping distance. Pattern Recognition, 2020 (PR, CCF-B类期刊，中科院一区)

  8. Huiqi Deng, Weifu Chen, Andy J. Ma, Qi Shen, Pong C. Yuen, Guocan Feng. Robust shapelets learning: Transform-invariant prototypes. Chinese Conference on Pattern Recognition and Computer Vision, 2018 (PRCV, CCF-C类会议)

  9. Haiyan Zhao, Hanjie Chen, Fan Yang, Ninghao Liu, Huiqi Deng, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Mengnan Du. Explainability for large language models: A survey. ACM Transactions on Intelligent Systems and Technology, 2024. (大模型可解释性综述，引用超 500 次)

  10. Huilin Zhou, Hao Zhang, Huiqi Deng, Dongrui Liu, Wen Shen, Shih-Han Chan, Quanshi Zhang. Explaining generalization power of a dnn using interactive concepts. AAAI Conference on Artificial Intelligence, 2024（AAAI; CCF-A类会议）

  11. Jie Ren, Mingjie Li, Qirui Chen, Huiqi Deng, Quanshi Zhang. Defining and quantifying the emergence of sparse concepts in dnns. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023. （CVPR; CCF-A类会议）


    AI 应用方向：

  12. Hongbin Pei, Yu Li, Huiqi Deng, Jingxin Hai, Pinghui Wang, Jie Ma, Jing Tao, Yuheng Xiong, Xiaohong Guan. Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing. International Conference on Machine Learning, 2024（ ICML; CCF-A类会议；Spotlight Paper 录用率3.5%；算法应用在KDD CUP 2024 Task 2挑战赛，获得铜牌）  

  13. Hongbin Pei, Taile Chen, Chen A, Huiqi Deng, Jing Tao, Pinghui Wang, Xiaohong Guan. HAGO-Net: Hierarchical Geometric Massage Passing for Molecular Representation Learning. AAAI Conference on Artificial Intelligence, 2024（AAAI; CCF-A类会议）

  14. Qingxiong Tan, Andy J. Ma, Mang Ye, Baoyao Yang, Huiqi Deng, Vincent Wai-Sun Wong, et al. UA-CRNN: Uncertainty-aware convolutional recurrent neural network for mortality risk prediction.   ACM international conference on information and knowledge management, 2019 (CIKM, CCF-B类会议)