Amortized Inference for Causal Structure Learning, NeurIPS 2022

A benchmarking suite for disentanglement algorithms, suited for evaluating robustness to correlated factors. Codebase for the paper "Disentanglement of Correlated Factors via Hausdorff Factorized S…

code for paper: Identifiability Guarantees for Causal Disentanglement from Soft Interventions

This is the repository for the Photorealistic Unreal Graphics (PUG) datasets for representation learning.

Sklearn-style implementations of model selection criteria for CATE estimation

Code repository of the paper "CITRIS: Causal Identifiability from Temporal Intervened Sequences" and "iCITRIS: Causal Representation Learning for Instantaneous Temporal Effects"

ACL 2022: Revisiting the Compositional Generalization Abilities of Neural Sequence Models

The repository contains lists of papers on causality and how relevant techniques are being used to further enhance deep learning era computer vision solutions.

Repository for "Differentiable Causal Discovery from Interventional Data"

Solving the causality pairs challenge (does A cause B) with ChatGPT

Visualizing representations with diffusion based conditional generative model.

Chicago undergraduate mathematics bibliography

A fast library for AutoML and tuning. Join our Discord: https://discord.gg/Cppx2vSPVP.

Library for the training and evaluation of object-centric models (ICML 2022)

Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style

We will keep updating the paper list about machine learning + causal theory. We also internally discuss related papers between NExT++ (NUS) and LDS (USTC) by week.

Code for ICE-BeeM paper - NeurIPS 2020

VAEs and nonlinear ICA: a unifying framework

Code for the paper "Contrastive Learning Inverts the Data Generating Process".

Realistic benchmark for different causal inference methods. The realism comes from fitting generative models to data with an assumed causal structure.

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows

Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization

Code for Environment Inference for Invariant Learning (ICML 2021 Paper)

TensorFlow implementation of 'Core', proposed in "Conditional Variance Penalties and Domain Shift Robustness".