Publications

[Google Scholar]
The code is at the Group Github.
(* denotes equal contribution, # denotes correspondence)

  Preprint

  2023

• Towards Understanding Generalization of Macro-AUC in Multi-label Learning [pdf]
  Guoqiang Wu#, Chongxuan Li, Yilong Yin
  In proc. of International Conference on Machine Learning (ICML), 2023.

• Revisiting Discriminative vs. Generative Classifiers: Theory and Implications [pdf]
  Chenyu Zheng, Guoqiang Wu, Fan Bao, Yue Cao, Chongxuan Li#, Jun Zhu
  In proc. of International Conference on Machine Learning (ICML), 2023.

• Toward Understanding Generative Data Augmentation [arXiv]
  Chenyu Zheng, Guoqiang Wu, Chongxuan Li#
  In proc. of Advances in Neural Information Processing Systems (NeurIPS), 2023.

• DiffAIL: Diffusion Adversarial Imitation Learning [arXiv]
  Bingzheng Wang, Guoqiang Wu#, Teng Pang, Yan Zhang, Yilong Yin#
  In proc. of AAAI Conference on Artificial Intelligence (AAAI), 2024.

  2021

• Rethinking and Reweighting the Univariate Losses for Multi-Label Ranking: Consistency and Generalization [pdf]
  Guoqiang Wu*, Chongxuan Li*, Kun Xu, and Jun Zhu
  In proc. of Advances in Neural Information Processing Systems (NeurIPS), 2021.

• Stability and Generalization of Bilevel Programming in Hyperparameter Optimization [pdf]
  Fan Bao*, Guoqiang Wu*, Chongxuan Li*, Jun Zhu, and Bo Zhang
  In proc. of Advances in Neural Information Processing Systems (NeurIPS), 2021.

• On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms [pdf]
  Shuyu Cheng, Guoqiang Wu, and Jun Zhu
  In proc. of Advances in Neural Information Processing Systems (NeurIPS), 2021.

  2020

• Multi-label classification: do Hamming loss and subset accuracy really conflict with each other? [pdf]
  Guoqiang Wu, and Jun Zhu.
  In proc. of Advances in Neural Information Processing Systems (NeurIPS), 2020

• Joint ranking SVM and binary relevance with robust low-rank learning for multi-label classification [url]
  Guoqiang Wu, Ruobing Zheng, Yingjie Tian and Dalian Liu
  Neural Networks, 2020

  2018

• Cost-sensitive multi-label learning with positive and negative label pairwise correlations [url]
  Guoqiang Wu, Yingjie Tian, and Dalian Liu
  Neural Networks, 2018

• A unified framework implementing linear binary relevance for multi-label learning [url]
  Guoqiang Wu, Yingjie Tian, and Chunhua Zhang
  Neurocomputing, 2018

• Privileged Multi-Target Support Vector Regression
  Guoqiang Wu, Yingjie Tian, and Dalian Liu
  In proc. of International Conference on Pattern Recognition (ICPR), 2018