Ph.D., Associate Professor

   School of Computer Science and Engineering

   Southeast University

   Email: is.jiaqi.lv@gmail.com & jiaqi.lv@seu.edu.cn

   I am a member of PAtttern Learning and Mining (PALM) Lab.

呂佳祺，博士，bet356手机版唯一官网登录副教授，bet356手机版唯一官网“紫金青年學者”。2021年于bet356手机版唯一官网獲得博士學位，2021-2023年任日本理化學研究所AIP中心博士後研究員。研究領域包括機器學習、深度學習，重點關注可信賴人工智能，當前的工作重點是從弱監督數據中進行學習和推理，旨在減少對大量标注數據的依賴，同時不犧牲模型的可靠性。在相關領域的國際頂級會議與期刊上（包括TPAMI, ICML, NeurIPS等）發表論文10餘篇，并擔任多個國際著名會議的程序員會委員、審稿人。

I'm currently an Associate Researcher at PALM Lab, the School of Computer Science and Engineering, Southeast University (SEU), Nanjing, China. My research interests lie in machine learning and deep learning, focusing on trustworthy AI. With a current emphasis on learning and reasoning from weakly supervised data, we aim to reducing our reliance on extensively annotated datasets without sacrificing the models' reliability. The ultimate goal is to make machine learning a tool for enhancing human decisions without compromising our ethical values or privacy. I received my Bachelor's and Doctorate degrees at SEU, under the guidance of Prof. Xin Geng. Following my graduation in 2021, I embarked on a postdoctoral journey at the RIKEN Center for Advanced Intelligence Project, Japan, collaborating with esteemed scholars such as Prof. Masashi Sugiyama and Dr. Gang Niu. This enriching experience spanned two years, after which I returned to my alma mater, SEU.

歡迎對機器學習、深度學習、弱監督學習、可信人工智能有興趣的同學加入我們一起工作！

對學生的期望：編程基礎紮實，有責任心，自驅力強，腳踏實地，勇于挑戰

對學生的承諾：平等與尊重的環境，無科研訓練外其他事務，共同努力探索知識的邊界

More Information:

Personal Webpage

Selected Publications:

1. Y. Liu*, J. Lv*, X Geng, and N Xu.Learning with Partial-label and unlabeled data: A uniform treatment for supervision redundancy and insufficiency. In Proceedings of 41st International Conference on Machine Learning (ICML 2024), PMLR, Vienna, Austria, Jul 21--27, 2024.

2. J. Lv, B. Liu, L. Feng, N. Xu, M. Xu, B. An, G. Niu, X. Geng, and M. Sugiyama. On the robustness of average losses for partial-label learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(5):2569–2583, 2024.

3. S. Xia*, J. Lv*, N. Xu, G. Niu, and X. Geng. Towards effective visual representations for partial-label learning. In Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023), pp. 15589--15598, Vancouver, British Columbia, Canada, Jun 18--22, 2023.

4. N. Xu, B. Liu, J. Lv, C. Qiao, and X. Geng. Progressive Purification for Instance-Dependent Partial Label Learning. In Proceedings of 40th International Conference on Machine Learning (ICML 2023), PMLR, vol. 202, pp. 38551--38565, Honolulu, Hawaii, USA, Jul 24--30, 2023.

5. C. Qiao, N. Xu, J. Lv, Y. Ren, and X. Geng. FREDIS: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning. In Proceedings of 40th International Conference on Machine Learning (ICML 2023), PMLR, vol. 202, pp. 28321--28336, Honolulu, Hawaii, USA, Jul 24--30, 2023.

6. S. Xia, J. Lv, N. Xu, and X. Geng. Ambiguity-Induced Contrastive Learning for InstanceDependent Partial Label Learning. In Proceedings of 31st International Joint Conference on Artificial Intelligence (IJCAI 2022), pp. 3615--3621, Vienna, Austria, Jul 23--29, 2022.

7. Z. Wu, J. Lv, and M. Sugiyama. Learning with Proper Partial Labels. Neural Computation, vol. 35, no. 1, pp. 58--81, 2023.

8. J. Lv, T. Wu, C. Peng, Y. Liu, N. Xu, and X. Geng. Compact Learning for Multi-Label Classification. Pattern Recognition, vol. 113, pp. 107833, 2021.

9. J. Lv, M. Xu, L. Feng, G. Niu, X. Geng, and M. Sugiyama. Progressive identification of true labels for partial-label learning. In Proceedings of 37th International Conference on Machine Learning (ICML 2020), PMLR, vol. 119, pp. 6500--6510, Online, Jul 12--18, 2020.

10. L. Feng, J. Lv, B. Han, M. Xu, G. Niu, X. Geng, B. An, and M. Sugiyama. Provably consistent partial-label learning. In Advances in Neural Information Processing Systems 33 (NeurIPS 2020), pp. 10948--10960, Online, Dec 6--12, 2020.

11. J. Lv, N. Xu, R. Zheng, and X. Geng. Weakly Supervised Multi-Label Learning via Label Enhancement. In Proceedings of 28th International Joint Conference on Artificial Intelligence (IJCAI 19), pp. 3101--3107, Macao, China, Aug 10--16, 2019.