3

RSGAN - daiwk-github博客

 1 year ago
source link: https://daiwk.github.io/posts/dl-rsgan.html
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.

首页 > 深度学习 > 正文

RSGAN

标签:RSGAN


节后收心困难?这15篇论文,让你迅速找回学习状态

Generating Reliable Friends via Adversarial Training to Improve Social Recommendation

http://github.com/Coder-Yu/RecQ

本文为发表在 ICDM 2019 的工作。论文提出了一种基于生成对抗训练框架的 social recommendation 模型,指出了现有社会化推荐模型中的关系缺失、噪声问题,并利用对抗训练改善了这些问题,提高了社会化推荐的效果。此外,以往基于 Policy Gradient 的离散 GAN 在训练时存在 reward 函数设计困难,收敛难等问题,本文利用重参数技巧,对模型进行了 End-to-End 的训练,绕开了 reward 函数,取得了很好的效果。

原创文章,转载请注明出处!
本文链接:http://daiwk.github.io/posts/dl-rsgan.html


comment here..

About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK