[其他] ICML-Disentangling Sampling and Labeling Bias for Learning in Large-output ... [推广有奖]

1关注
167
粉丝

已卖：5678份资源

泰斗

还不是VIP/贵宾

威望: 0 级
论坛币: 13312 个
通用积分: 718.1716
学术水平: 459 点
热心指数: 484 点
信用等级: 414 点
经验: 116269 点
帖子: 4686
精华: 0
在线时间: 16731 小时
注册时间: 2013-1-2
最后登录: 2026-1-21

楼主

Mujahida

发表于 2025-8-10 16:36:52 |AI写论文

是否 +2 论坛币

k人参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Disentangling Labeling and Sampling Bias for Learning in Large-output Spaces

  Ankit Singh Rawat 1 Aditya Krishna Menon 1 Wittawat Jitkrittum 1 Sadeep Jayasumana 1 Felix X. Yu 1
               Sashank J. Reddi 1 Sanjiv Kumar 1

         Abstract             closely a scheme approximates the unsampled loss on the
                              full label set. This bias is well understood for sampled
Negative sampling schemes enable efficient train-
                              s ...