[其他] ICML-A Tale of Two Efficient and Informative Negative Sampling Distributions [推广有奖]

1关注
167
粉丝

已卖：5640份资源

泰斗

还不是VIP/贵宾

威望: 0 级
论坛币: 13322 个
通用积分: 711.3950
学术水平: 459 点
热心指数: 484 点
信用等级: 414 点
经验: 115899 点
帖子: 4676
精华: 0
在线时间: 16723 小时
注册时间: 2013-1-2
最后登录: 2025-12-14

楼主

Mujahida

发表于 2025-8-11 09:39:27 |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

A Tale of Two Efficient and Informative Negative Sampling Distributions

   Shabnam Daghaghi 1 Tharun Medini 1 Nicholas Meisburger 2 Beidi Chen 3 Mengnan Zhao 1
               Anshumali Shrivastava 2 1

         Abstract             AI problems are currently modeled as massive multiclass
Softmax classifiers with a very large number of    or multilabel problems leading to a drastic improvement
classes naturally occur in many applications such    over prior work. For example,  ...