 数据跨域问题(Domain generalization): 解决实际应用中模型的训练测试不一致问题，主要 研究如何将测试数据分布转化到训练分布上，或者增广训练数据尽量覆盖测试情况。 

 迁移学习(Transfer learning): 将大规模数据所蕴含的知识迁移到小数据的学习过程中，从 而提升深度神经网络在小数据上的性能。 

 终身学习(Lifelong learning): 通过模拟一个生成式内存来记住一系列的顺序的任务数据 的生成过程，达到缓解终身学习过程中的灾难性遗忘问题的目的。

[1] Yulai Cong, Miaoyun Zhao. Big Learning: A Universal Machine Learning Paradigm?[J]. arXiv preprint arXiv:2207.03899, 2022. 

[2] Miaoyun Zhao, Yulai Cong, Lawrence Carin,“On Leveraging Pretrained GANs for Generation with Limited Data,”International Conference on Machine Learning (ICML 2020), July 2020. (CCF 推荐 A 类) 

[3] Miaoyun Zhao, Yulai Cong, Lawrence Carin, “Bridging Maximum Likelihood and Adversarial Learning via alpha-Divergence,” Association for the Advance of Artificial Intelligence (AAAI 2020), Feb. 2020, 学术报告. (CCF 推荐 A 类) 

[4] Miaoyun Zhao, Li Wang, Jiawei Chen, Dong Nie, Yulai Cong, Sahar Ahmad, Angela Ho, Peng Yuan, Steve H. Fung, Hannah H. Deng, James Xia, Dinggang Shen. “Craniomaxillofacial Bony Structures Segmentation from MRI with Deep-Supervision Adversarial Learning,” International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2018), Sep. 2018. 

[5] Miaoyun Zhao, Licheng Jiao, Jie Feng, Tianyu Liu, “A simplified low rank and sparse graph for semi-supervised learning,” [J]. Neurocomputing, 140 (2014): 84-96. (SCI 二区) 

[6] Miaoyun Zhao, Licheng Jiao, Wenping Ma, Hongying Liu, Shuyuan Yang, “Classification and saliency detection by semi-supervised low-rank representation,” [J]. Pattern Recognition, 51 (2016): 281-294. (SCI 一区) 

[7] Yulai Cong, Miaoyun Zhao , Jianqiao Li, Junya Chen, Lawrence Carin, “GO Hessian for Expectation-Based Objectives.” Association for the Advance of Artificial Intelligence (AAAI 2021). (CCF 推荐 A 类) 、

[8] Yulai Cong, Miaoyun Zhao , Jianqiao Li, Sijia Wang, Lawrence Carin. GAN Memory with No Forgetting. Advances in Neural Information Processing Systems (NeurIPS 2020). (CCF 推荐 A 类) 

[9] Yulai Cong, Miaoyun Zhao, Ke Bai, Lawrence Carin, “GO Gradient for Expectation-Based Objectives,” International Conference on Learning Representations (ICLR 2019), May 2019