Giter Site home page Giter Site logo

Comments (6)

KaihuaTang avatar KaihuaTang commented on August 21, 2024

可以参考“An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies”这篇文章。如果不用normalization相当于de-confound不彻底,会导致之后TDE不work,即,因为confound path的存在,所以得不到direct effect

from long-tailed-recognition.pytorch.

HX-idiot avatar HX-idiot commented on August 21, 2024

follow了一下,所以您是将当前观测到的样本当作是从do(x)之后的distribution中采样来的,因此给他们赋予了一个$weight = 1/P(x|M=m)$对吧?那为什么P(x|M=m) 可以近似为 L2-norm呢?这是基于什么得出的呢?

from long-tailed-recognition.pytorch.

KaihuaTang avatar KaihuaTang commented on August 21, 2024

关于怎么设计这个normalization,我们还是偏经验主义。因为Propensity Score的**只告诉我们需要对effect做balancing,但具体怎么设计其实是很开放的。

from long-tailed-recognition.pytorch.

sky186 avatar sky186 commented on August 21, 2024

@KaihuaTang
您好,您有试过 例如加入 circle loss ,数据不平衡的训练中加入该CausalNormClasseifer, 因为您的论文中有特征图的可视化,发现学习到的特征图更紧凑, 所以考虑 是否可以加入CausalNormClasseifer 分支 当作辅助训练,

from long-tailed-recognition.pytorch.

KaihuaTang avatar KaihuaTang commented on August 21, 2024

@KaihuaTang
您好,您有试过 例如加入 circle loss ,数据不平衡的训练中加入该CausalNormClasseifer, 因为您的论文中有特征图的可视化,发现学习到的特征图更紧凑, 所以考虑 是否可以加入CausalNormClasseifer 分支 当作辅助训练,

我没有试过,听起来好像挺靠谱的。你可以试一下看work不work

from long-tailed-recognition.pytorch.

sky186 avatar sky186 commented on August 21, 2024

@KaihuaTang
好的,我试一下,然后反馈一下。
我是直接加一个 CausalNormClasseifer + crosse+entropy loss, 使用它有什么超参数需要注意的吗?

from long-tailed-recognition.pytorch.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.