Giter VIP home page Giter VIP logo

causalrepid's Introduction

Interventional Causal Representation Learning

Reproduce Results for the Polynomial Decoder Datasets

Generate Data

  • python scripts/main_exps.py --case data --target_latent uniform
  • python scripts/main_exps.py --case data --target_latent uniform_corr
  • python scripts/main_exps.py --case data --target_latent gaussian_mixture
  • python scripts/main_exps.py --case data --target_latent scm_sparse
  • python scripts/main_exps.py --case data --target_latent scm_dense

Table 2: Observational Data Case

Train Models

  • bash main_slurm_launcher 0 ae_poly 1e-3
  • bash main_slurm_launcher 0 ae_poly 5e-4
  • bash main_slurm_launcher 0 ae_poly 1e-4

Evaluate Models

  • python scripts/main_exps.py --case test --method_type ae_poly --lr 1e-3 --intervention_case 0
  • python scripts/main_exps.py --case test --method_type ae_poly --lr 5e-4 --intervention_case 0
  • python scripts/main_exps.py --case test --method_type ae_poly --lr 1e-4 --intervention_case 0

Log Results

  • python scripts/main_exps.py --case log --method_type ae_poly --intervention_case 0

Table 3: Interventional Data Case

Run all the commands stated above for the observational case (Table 2) with the flag --intervention_case set as 1

Running experiments for Neural Network Decoder

Run all the commands stated above for the observational case (Table 2) with the flag --method_type set as 'ae'.

Reproduce Results for the Image Dataset

Table 4: Image Dataset

Train Models

  • bash main_slurm_launcher_image.sh balls_uniform_none
  • bash main_slurm_launcher_image.sh balls_scm_linear
  • bash main_slurm_launcher_image.sh balls_scm_non_linear

Evaluate Models

  • python scripts/main_exps_images.py --case test --target_latent balls_uniform_none
  • python scripts/main_exps_images.py --case test --target_latent balls_scm_linear
  • python scripts/main_exps_images.py --case test --target_latent balls_scm_non_linear

Log Results

  • python scripts/main_exps_images.py --case log

License

This source code is released under the MIT license, included here.

causalrepid's People

Contributors

divyat09 avatar

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.