ICLR 全称为 International Conference on Learning Representations（国际学习表征会议），自 2013 年开始每年举办一次，2021 年将举办第九届会议，是国际公认的深度学习领域的顶级会议。ICLR在所有科学出版物中排名第17，超过了NeurIPS、ICCV和ICML（在AI顶会中仅落后于CVPR，该榜单的前三名是 Nature、新英格兰医学杂志和 Science。）
ICLR 2021一共有2997篇有效论文投稿，最后860篇被接收，被接收论文中有53篇论文被接收为Oral、114篇论文被接收为Spotlight、693篇论文被接收为Poster。
必赢71886网址登录必赢626net入口机器学习研究中心林宙辰教授、王立威教授和王奕森助理教授有6篇论文被ICLR 2021收录，包括2篇Spotlight。
被收录论文如下：
[1] Zhengyang Geng, Meng-Hao Guo, Hongxu Chen, Xia Li, Ke Wei, and Zhouchen Lin, “Is Attention Better Than Matrix Decomposition?”
[2] Ke Sun, Zhouchen Lin, and Zhanxing Zhu, “AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models”
[3] Xiaoyu Chen, Jiachen Hu, Lihong Li, Liwei Wang, “Efficient Reinforcement Learning in Factored MDPs with Application to Constrained RL”
[4] Xin Wang, Jie Ren, Shuyun Lin, Xiangming Zhu, Yisen Wang, Quanshi Zhang, “Towards A Unified Understanding and Improving of Adversarial Transferability”
[5] Yang Bai, Yuyuan Zeng, Yong Jiang, Shu-Tao Xia, Xingjun Ma, Yisen Wang, “Improving Adversarial Robustness via Channel-wise Activation Suppressing” (Spotlight)
[6] Hanxun Huang, Xingjun Ma, Sarah Monazam Erfani, James Bailey, Yisen Wang, “Unlearnable Examples: Making Personal Data Unexploitable” (Spotlight)
