基本信息
浏览量:55
职业迁徙
个人简介
I am mostly interested in developing theoretical understandings and principled designs for machine learning in the following scenarios:
Learning with limited supervision. I am mostly interested in Self-Supervised Learning (SSL) that allows learning richful features from massive unlabeled data, laying the foundation for large-scale foundation models.
Learning under distribution shifts. In real-world applications, data distributions always shift. I explore how model failures arise and how to build Robust Models against adversarial and real-world distribution shifts.
Learning from graphs. Graph is a common language to model relationships among entities with wide applications. I am interested in the inherent mechanisms of Graph Neural Networks and Transformers.
Learning with limited supervision. I am mostly interested in Self-Supervised Learning (SSL) that allows learning richful features from massive unlabeled data, laying the foundation for large-scale foundation models.
Learning under distribution shifts. In real-world applications, data distributions always shift. I explore how model failures arise and how to build Robust Models against adversarial and real-world distribution shifts.
Learning from graphs. Graph is a common language to model relationships among entities with wide applications. I am interested in the inherent mechanisms of Graph Neural Networks and Transformers.
研究兴趣
论文共 42 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
arxiv(2024)
引用0浏览0引用
0
0
ICLR 2024 (2024)
引用0浏览0引用
0
0
ICLR 2024 (2024)
引用0浏览0引用
0
0
CoRR (2024)
引用0浏览0EI引用
0
0
CoRR (2023)
引用0浏览0EI引用
0
0
CoRR (2023): 6448-6467
引用6浏览0EI引用
6
0
ICLR 2023 (2023)
引用0浏览0引用
0
0
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn