Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Deep Learning Recommendation Model for Personalization and Recommendation Systems, Naumov+, Facebook, arXiv‘19 #397

Open
AkihikoWatanabe opened this issue Jul 2, 2021 · 3 comments

Comments

@AkihikoWatanabe
Copy link
Owner

https://arxiv.org/pdf/1906.00091.pdf

@AkihikoWatanabe
Copy link
Owner Author

AkihikoWatanabe commented Jul 2, 2021

Facebookが開発したopen sourceのDeepな推薦モデル(MIT Licence)。

モデル自体はシンプルで、continuousなfeatureをMLPで線形変換、categoricalなfeatureはembeddingをlook upし、それぞれfeatureのrepresentationを獲得。
その上で、それらをFactorization Machines layer(second-order)にぶちこむ。すなわち、Feature間の2次の交互作用をembedding間のdot productで獲得し、これを1次項のrepresentationとconcatしMLPにぶちこむ。最後にシグモイド噛ませてCTRの予測値とする。

image

@AkihikoWatanabe
Copy link
Owner Author

@AkihikoWatanabe
Copy link
Owner Author

Parallelism以後のセクションはあとで読む

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant