李长春现任金沙威尼斯欢乐娱人城准聘副教授(研究员),博士研究生导师。博士毕业于金沙威尼斯欢乐娱人城,主要研究方向是机器学习、弱监督学习、半监督学习、虚假信息治理等领域。近五年共计发表学术论文近20篇,
包括以第一/通讯作者在ICML、ICLR、ACL、WWW、AAAI、IJCAI等中国计算机学会推荐A类会议发表论文多篇;相关工作得到了国内外学者的认可和关注,他引400余次,h-index 11。
🔥现在招收2025年入学博士1名和硕士研究生3名。常年招收科研助理(大一至大四均可),将提供计算资源及奖助学金,欢迎对于机器学习研究有兴趣、目标发表顶会顶刊、想要升学/出国的同学联系
(有任何疑问欢迎邮件预约面谈~☕)
工作经历
2024.07 —— 至今 金沙威尼斯欢乐娱人城 准聘副教授/研究员 博士生导师
2022.07 —— 2024.07 金沙威尼斯欢乐娱人城 “鼎新学者”博士后/助理研究员
教育经历
2015.09 —— 2022.06 吉林大学 金沙威尼斯欢乐娱人城 硕博连读
2011.09 —— 2015.07 金沙威尼斯欢乐娱人城 金沙威尼斯欢乐娱人城 学士
科研项目
1. 金沙威尼斯欢乐娱人城鼎新学者支持计划项目, 2022-06至2024-06, 主持
2. 国家自然科学基金面上项目,分布外数据场景下图表示学习可泛化性和可解释性研究,2024-01至2027-12,参与
3. 国家自然科学基金面上项目,高精度稳定的黑盒变分推理关键问题研究,2019-01至2022-12,参与
论文发表
在弱监督学习、半监督学习等领域发表学术论文近20篇,部分论文信息如下(完整列表详见学术主页):
[1] Changchun Li (李长春), Yuanchao Dai, Lei Feng, Ximing Li*, Bing Wang, Jihong Ouyang. Positive and Unlabeled Learning with Controlled Probability Boundary Fence, in Proceedings of the 41st International Conference on Machine Learning (ICML 2024). (CCF-A类会议长文)
[2] Ximing Li, Yuanchao Dai, Bing Wang, Changchun Li* (李长春), Renchu Guan, Fangming Gu, Jihong Ouyang. WPML3CP: Wasserstein Partial Multi-Label Learning with Dual Label Correlation Perspectives, In the International Joint Conference on Artificial Intelligence (IJCAI 2024). (CCF-A类会议长文)
[3] Ximing Li, Yuanzhi Jiang, Changchun Li* (李长春), Yiyuan Wang, Jihong Ouyang. Learning with Partial Labels from Semi-supervised Perspective, in Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2023), 8666-8674.(CCF-A类会议长文)
[4] Changchun Li (李长春), Ximing Li*, Lei Feng, Jihong Ouyang. Who is Your Right Mixup Partner in Positive and Unlabeled Learning, International Conference on Learning Representations (ICLR 2022).(清华大学计算机学科推荐A类会议长文)
[5] Changchun Li (李长春), Ximing Li#*, Jihong Ouyang*. Semi-supervised Text Classification with Balanced Deep Representation Distributions, in Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL 2021), 5044-5053.(CCF-A类会议长文)
[6] Changchun Li (李长春), Ximing Li, Jihong Ouyang. Detecting the Fake Candidate Instances: Ambiguous Label Learning with Generative Adversarial Networks, in Proceedings of the ACM International Conference on Information and Knowledge Management (CIKM 2021), 903-912. (CCF-B 类会议长文)
[7] Changchun Li (李长春), Ximing Li, Jihong Ouyang. Learning with Noisy Partial Labels by Simultaneously Leveraging Global and Local Consistencies, in Proceedings of the ACM International Conference on Information and Knowledge Management (CIKM 2020), 725-734. (CCF-B类会议长文)
[8] Changchun Li (李长春), Ximing Li, Jihong Ouyang, Yiming Wang. Semantics-assisted Wasserstein Learning for Topic and Word Embeddings, in Proceedings of the IEEE International Conference on Data Mining (ICDM 2020), 292-301. (CCF-B 类会议长文)
[9] Changchun Li (李长春), Jihong Ouyang, Ximing Li*. Classifying Extremely Short Texts by Exploiting Semantic Centroids in Word Mover's Distance Space, in The World Wide Web Conference (WWW 2019), 939-949.(CCF-A类会议长文)
获奖情况
l 吉林省优秀博士学位论文
l ACM China优秀博士论文奖
学术审稿
受邀担任NeurIPS、ICLR、ACL、ACM MM等CCF-A类会议,Expert Systems with Applications、Information Processing and Management、Neurocomputing、Knowledge-Based Systems等国际期刊审稿人。