Code for SyncTwin: Treatment Effect Estimation with Longitudinal Outcomes (NeurIPS 2021)

Overview

SyncTwin: Treatment Effect Estimation with Longitudinal Outcomes (NeurIPS 2021)

SyncTwin is a treatment effect estimation method tailored for observational studies with longitudinal data. Specifically, it applies to the LIP setting: Longitudinal, Irregular and Point treatment. In these studies, the covariates are observed at irregular intervals leading to treatment allocation; the outcomes are measured longitudinally before and after the treatment; the treatment is assigned at a specific time point and stays unchanged during the study.

The key insight of SyncTwin is to fully leverage the pre-treatment outcomes. It uses the temporal structure in the outcome time series to improve the accuracy of counterfactual prediction. It further uses the pre-treatment outcomes to control the estimation error on the individual level. Finally, the method enables interpretability by example: the user can examine the key contributing examples that leads to the estimate.

Installation

To run the code locally, make sure to first install the required python packages specified in requirements.txt. Python 3.7 is recommended for best compatibility. Note that tensorflow and GPy are only needed for running the benchmarks. The directory clairvoyance contains a streamlined version of the clairvoyance library. It is used to run the benchmarks CRN and RMSN.

For some benchmarks (SC, MC-NNM, 1NN), we use their public implementations in the R language. To run these benchmarks, please install R and the dependencies listed in requirements_R.txt.

For coda users, an environment YAML file environment.yml is provided, which includes both Python and R dependencies.

Usage

Scripts for reproducing paper experiments are provided under the directory experiments/.

The reproduce_all.sh shell script contains commands to reproduce all tables and figures in the paper. The Fig[x].sh or Tab[x].sh shell script contain commands to generate results for individual figures or tables. The Fig[x].ipynb notebooks contain commands to create the visualizations. The results will be written in the results folder. For instance, Tab2_C1_MAE.txt corresponds to the first Column of Table 2.

An implementation of SyncTwin is provided in the file SyncTwin.py. Note that SyncTwin is a general framework agnostic to the exact architectural choice of encoder and decoder. In this implementation, we use attentive GRU-D encoder and time-LSTM decoder. In the simulations, SyncTwin is trained in pkpd_sim3_model_training.py.

Citation

If you find the software useful, please consider citing the following paper:

@inproceedings{synctwin2021,
  title={SyncTwin: Treatment Effect Estimation with Longitudinal Outcomes},
  author={Qian, Zhaozhi and Zhang, Yao and Bica, Ioana and Wood, Angela and van der Schaar, Mihaela},
  booktitle={Advances in neural information processing systems},
  year={2021}
}

License

Copyright 2021, Zhaozhi Qian.

This software is released under the MIT license.

Owner
Zhaozhi Qian
Zhaozhi Qian
This is a Keras-based Python implementation of DeepMask- a complex deep neural network for learning object segmentation masks

NNProject - DeepMask This is a Keras-based Python implementation of DeepMask- a complex deep neural network for learning object segmentation masks. Th

189 Nov 16, 2022
RL and distillation in CARLA using a factorized world model

World on Rails Learning to drive from a world on rails Dian Chen, Vladlen Koltun, Philipp Krähenbühl, arXiv techical report (arXiv 2105.00636) This re

Dian Chen 131 Dec 16, 2022
OpenGAN: Open-Set Recognition via Open Data Generation

OpenGAN: Open-Set Recognition via Open Data Generation ICCV 2021 (oral) Real-world machine learning systems need to analyze novel testing data that di

Shu Kong 90 Jan 06, 2023
Multi-Scale Geometric Consistency Guided Multi-View Stereo

ACMM [News] The code for ACMH is released!!! [News] The code for ACMP is released!!! About ACMM is a multi-scale geometric consistency guided multi-vi

Qingshan Xu 118 Jan 04, 2023
[NeurIPS 2021] Garment4D: Garment Reconstruction from Point Cloud Sequences

Garment4D [PDF] | [OpenReview] | [Project Page] Overview This is the codebase for our NeurIPS 2021 paper Garment4D: Garment Reconstruction from Point

Fangzhou Hong 112 Dec 23, 2022
coldcuts is an R package to automatically generate and plot segmentation drawings in R

coldcuts coldcuts is an R package that allows you to draw and plot automatically segmentations from 3D voxel arrays. The name is inspired by one of It

2 Sep 03, 2022
This is the code for our paper "Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text"

Iconary This is the code for our paper "Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text". It includes the

AI2 6 May 24, 2022
The official PyTorch implementation of paper BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition

BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition Boyan Zhou, Quan Cui, Xiu-Shen Wei*, Zhao-Min Chen This repo

Megvii-Nanjing 616 Dec 21, 2022
Deep Learning segmentation suite designed for 2D microscopy image segmentation

Deep Learning segmentation suite dessigned for 2D microscopy image segmentation This repository provides researchers with a code to try different enco

7 Nov 03, 2022
A Flexible Generative Framework for Graph-based Semi-supervised Learning (NeurIPS 2019)

G3NN This repo provides a pytorch implementation for the 4 instantiations of the flexible generative framework as described in the following paper: A

Jiaqi Ma 14 Oct 11, 2022
A flexible framework of neural networks for deep learning

Chainer: A deep learning framework Website | Docs | Install Guide | Tutorials (ja) | Examples (Official, External) | Concepts | ChainerX Forum (en, ja

Chainer 5.8k Jan 06, 2023
[NAACL & ACL 2021] SapBERT: Self-alignment pretraining for BERT.

SapBERT: Self-alignment pretraining for BERT This repo holds code for the SapBERT model presented in our NAACL 2021 paper: Self-Alignment Pretraining

Cambridge Language Technology Lab 104 Dec 07, 2022
UniFormer - official implementation of UniFormer

UniFormer This repo is the official implementation of "Uniformer: Unified Transf

SenseTime X-Lab 573 Jan 04, 2023
An Exact Solver for Semi-supervised Minimum Sum-of-Squares Clustering

PC-SOS-SDP: an Exact Solver for Semi-supervised Minimum Sum-of-Squares Clustering PC-SOS-SDP is an exact algorithm based on the branch-and-bound techn

Antonio M. Sudoso 1 Nov 13, 2022
Code release for Convolutional Two-Stream Network Fusion for Video Action Recognition

Convolutional Two-Stream Network Fusion for Video Action Recognition

Christoph Feichtenhofer 676 Dec 31, 2022
Simple, but essential Bayesian optimization package

BayesO: A Bayesian optimization framework in Python Simple, but essential Bayesian optimization package. http://bayeso.org Online documentation Instal

Jungtaek Kim 74 Dec 05, 2022
a general-purpose Transformer based vision backbone

Swin Transformer By Ze Liu*, Yutong Lin*, Yue Cao*, Han Hu*, Yixuan Wei, Zheng Zhang, Stephen Lin and Baining Guo. This repo is the official implement

Microsoft 9.9k Jan 08, 2023
Best practices for segmentation of the corporate network of any company

Best-practice-for-network-segmentation What is this? This project was created to publish the best practices for segmentation of the corporate network

2k Jan 07, 2023
A template repository for submitting a job to the Slurm Cluster installed at the DISI - University of Bologna

Cluster di HPC con GPU per esperimenti di calcolo (draft version 1.0) Per poter utilizzare il cluster il primo passo è abilitare l'account istituziona

20 Dec 16, 2022
Hardware accelerated, batchable and differentiable optimizers in JAX.

JAXopt Installation | Examples | References Hardware accelerated (GPU/TPU), batchable and differentiable optimizers in JAX. Installation JAXopt can be

Google 621 Jan 08, 2023