Skip to content
@vanderschaarlab

van_der_Schaar \LAB

We are creating cutting-edge machine learning methods and applying them to drive a revolution in healthcare.
README.md

van der Schaar Lab

Software libraries

Name About Repo Cite
TemporAI A Machine Learning-centric time-series library for medicine supporting tasks like: time-to-event (survival) analysis, treatment effects, and prediction. temporai Citation
SynthCity SynthCity is a powerful library for generating and evaluating synthetic data for privacy, fairness and data augmentation. synthcity Citation
📊 Interpretability Suite A collection of Machine Learning interpretability methods - the methods aim to provide an insight into why a model has made a given prediction. interpretability ---
🏥 AutoPrognosis 2.0 AutoPrognosis 2.0 is a framework that leverages the power of AutoML for tabular data in a flexible and interpretable way. autoprognosis Citation

Research by topic

AutoML

Paper Code Journal/Conference
AutoPrognosis 2.0: Democratizing Diagnostic and Prognostic Modeling in Healthcare with Automated Machine Learning Code pending, 2022
HyperImpute: Generalized Iterative Imputation with Automatic Model Selection Code ICML 2022
Clairvoyance: A Pipeline Toolkit for Medical Time Series Code ICLR 2021
Temporal Quilting for Survival Analysis Code AISTATS 2019
AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning Code ICML 2018
Stepwise Model Selection for Sequence Prediction via Deep Kernel Learning Code AISTATS 2020

Causal Inference

Paper Code Journal/Conference
MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanisms Code NeurIPS 2021
DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks Code NeurIPS 2021
CASTLE: Regularization via Auxiliary Causal Graph Discovery Code NeurIPS 2020

Data-centric AI & reliable ML

Paper Code Journal/Conference
Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data Code NeurIPS 2022
Data-SUITE: Data-centric identification of in-distribution incongruous examples Code ICML 2022

Data imputation

Paper Code Journal/Conference
To Impute or not to Impute? Missing Data in Treatment Effect Estimation Code AISTATS 2023
HyperImpute: Generalized Iterative Imputation with Automatic Model Selection Code ICML 2022
MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanisms Code NeurIPS 2021
VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain Code NeurIPS 2020
ASAC: Active Sensing using Actor-Critic Models Code MLHC 2019
GAIN: Missing Data Imputation using Generative Adversarial Nets Code ICML 2018
Deep Sensing: Active Sensing using Multi-directional Recurrent Neural Networks Code ICLR 2018

Differential equations

Paper Code Journal/Conference
Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations Code ICML 2022
Neural Laplace: Learning diverse classes of differential equations in the Laplace domain Code ICML 2022
Neural graphical modelling in continuous-time: consistency guarantees and algorithms Code ICLR 2022
D-CODE: Discovering Closed-form ODEs from Observed Trajectories Code ICLR 2022
Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression Code NeurIPS 2021
Policy Analysis using Synthetic Controls in Continuous-Time Code ICML 2021

Feature selection

Paper Code Journal/Conference
Composite Feature Selection Using Deep Ensembles Code NeurIPS 2022
KnockoffGAN: Generating Knockoffs for Feature Selection using Generative Adversarial Networks Code ICLR 2019
ASAC: Active Sensing using Actor-Critic Models Code MLHC 2019
Deep Sensing: Active Sensing using Multi-directional Recurrent Neural Networks Code ICLR 2018

Interpretability and Explainability

Paper Code Journal/Conference
Deep Generative Symbolic Regression Code ICLR 2023
Concept Activation Regions: A Generalized Framework For Concept-Based Explanations Code NeurIPS 2022
Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability Code NeurIPS 2022
Label-Free Explainability for Unsupervised Models Code ICML 2022
Explaining Latent Representations with a Corpus of Examples Code NeurIPS 2021
Explaining Time Series Predictions with Dynamic Masks Code ICML 2021
Learning outside the Black-Box: The pursuit of interpretable models Code NeurIPS 2020
Demystifying Black-box Models with Symbolic Metamodels Code NeurIPS 2019
INVASE: Instance-wise Variable Selection using Neural Networks Code ICLR 2019

Organ Transplantation Allocation

Paper Code Journal/Conference
Learning Queueing Policies for Organ Transplantation Allocation using Interpretable Counterfactual Survival Analysis Code ICML 2021
Learning Matching Representations for Individualized Organ Transplantation Allocation Code AISTATS 2021
OrganITE: Optimal transplant donor organ offering using an individual treatment effect Code NeurIPS 2020

Privacy-preserving ML & Synthetic data

Paper Code Journal/Conference
DOMIAS: Membership Inference Attacks against Synthetic Data through Overfitting Detection Code AISTATS 2023
SurvivalGAN: Generating Time-to-Event Data for Survival Analysis Code AISTATS 2023
Synthcity: facilitating innovative use cases of synthetic data in different data modalities Code ---
How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models Code ICML 2022
DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks Code NeurIPS 2021
Generative Time-series Modeling with Fourier Flows Code ICLR 2021
Time-series Generative Adversarial Networks Code NeurIPS 2019
PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees Code ICLR 2019
Anonymization Through Data Synthesis Using Generative Adversarial Networks (ADS-GAN) Code IEEE 2018
Differentially Private Bagging: Improved Utility and Cheaper Privacy than Subsample-and-Aggregate Code NeurIPS 2019

Reinforcement Learning

Paper Code Journal/Conference
Inverse Contextual Bandits: Learning How Behavior Evolves over Time Code ICML 2022
Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies Code ICLR 2022
Inferring Lexicographically-Ordered Rewards from Preferences Code AAAI 2022
Invariant Causal Imitation Learning for Generalizable Policies Code NeurIPS 2021
The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation Code NeurIPS 2021
Closing the loop in medical decision support by understanding clinical decision-making: A case study on organ transplantation Code NeurIPS 2021
Inverse Decision Modeling: Learning Interpretable Representations of Behavior Code ICML 2021
Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning Code ICLR 2021
Scalable Bayesian Inverse Reinforcement Learning Code ICLR 2021
Strictly Batch Imitation Learning by Energy-based Distribution Matching Code NeurIPS 2020
ASAC: Active Sensing using Actor-Critic Models Code MLHC 2019

Survival Analysis

Paper Code Journal/Conference
SurvivalGAN: Generating Time-to-Event Data for Survival Analysis Code AISTATS 2023
DeepHit: A Deep Learning Approach to Survival Analysis with Competing Risks Code AAAI 2018
Deep Multi-task Gaussian Processes for Survival Analysis with Competing Risks Code NIPS 2017

Time Series analysis

Paper Code Journal/Conference
Conformal Time-series Forecasting Code NeurIPS 2021
Explaining Time Series Predictions with Dynamic Masks Code ICML 2021
Generative Time-series Modeling with Fourier Flows Code ICLR 2021
Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders Code ICML 2020
Temporal Phenotyping using Deep Predicting Clustering of Disease Progression Code ICML 2020
Time-series Generative Adversarial Networks Code NeurIPS 2019
Dynamic-DeepHit: A Deep Learning Approach for Dynamic Survival Analysis with Competing Risks based on Longitudinal Data Code IEEE

Treatment Effects

Paper Code Journal/Conference
To Impute or not to Impute? Missing Data in Treatment Effect Estimation Code AISTATS 2023
Estimating Multi-cause Treatment Effects via Single-cause Perturbation Code NeurIPS 2021
SyncTwin: Treatment Effect Estimation with Longitudinal Outcomes Code NeurIPS 2021
Really Doing Great at Estimating CATE? A Critical Look at ML Benchmarking Practices in Treatment Effect Estimation Code NeurIPS 2021
On Inductive Biases for Heterogeneous Treatment Effect Estimation Code NeurIPS 2021
Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithms Code AISTATS 2021
Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks Code NeurIPS 2020
Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders Code ICML 2020
GANITE: Estimation of Individualized Treatment Effects using Generative Adversarial Nets Code ICLR 2018
Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes Code NIPS 2017
Robust Recursive Partitioning for Heterogeneous Treatment Effects with Uncertainty Quantification Code NeurIPS 2020
Learning Overlapping Representations for the Estimation of Individualized Treatment Effects Code AISTATS 2020
Estimating Counterfactual Treatment Outcomes over Time through Adversarially Balanced Representations Code ICLR 2020
Gradient Regularized V-Learning for Dynamic Treatment Regimes Code NeurIPS 2020
Contextual Constrained Learning for Dose-Finding Clinical Trials Code AISTATS 2020
Limits of Estimating Heterogeneous Treatment Effects: Guidelines for Practical Algorithm Design Code ICML 2018

Uncertainty estimation

Paper Code Journal/Conference
Conformal Time-series Forecasting Code NeurIPS 2021
Frequentist Uncertainty in Recurrent Neural Networks via Blockwise Influence Functions Code ICML 2020
Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions Code ICML 2020
RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks Code ICML 2018
Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift Code

Misc

Paper Code Journal/Conference
Scalable Bayesian Inverse Reinforcement Learning Code ICLR 2021
When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes Code NeurIPS 2020
Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift Code ICML 2020
Learning Dynamic and Personalized Comorbidity Networks from Event Data using Deep Diffusion Processes Code AISTATS 2020
Conditional Independence Testing using Generative Adversarial Networks Code NeurIPS 2019
Attentive State-Space Modeling of Disease Progression Code NeurIPS 2019
Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes Code NIPS 2017

Older work

For the monorepo with older research works, see https://github.com/vanderschaarlab/mlforhealthlabpub.

Pinned Loading

  1. mlforhealthlabpub mlforhealthlabpub Public

    Machine Learning and Artificial Intelligence for Medicine.

    Python 433 172

  2. clairvoyance clairvoyance Public

    Clairvoyance: a Unified, End-to-End AutoML Pipeline for Medical Time Series

    Jupyter Notebook 124 29

Repositories

Showing 10 of 106 repositories
  • climb Public Forked from DrShushen/climb

    CliMB: An AI-enabled Partner for Clinical Predictive Modeling

    vanderschaarlab/climb’s past year of commit activity
    Python 7 Apache-2.0 3 1 0 Updated Dec 17, 2024
  • SMART_Testing Public Forked from pauliusrauba/SMART_Testing
    vanderschaarlab/SMART_Testing’s past year of commit activity
    Python 0 1 0 0 Updated Dec 10, 2024
  • Self_Healing_ML Public Forked from pauliusrauba/Self_Healing_ML
    vanderschaarlab/Self_Healing_ML’s past year of commit activity
    Jupyter Notebook 0 1 0 0 Updated Dec 10, 2024
  • autoprognosis Public

    A system for automating the design of predictive modeling pipelines tailored for clinical prognosis.

    vanderschaarlab/autoprognosis’s past year of commit activity
    Python 122 Apache-2.0 26 10 1 Updated Dec 2, 2024
  • TRIAGE Public Forked from seedatnabeel/TRIAGE

    TRIAGE: Characterizing and auditing training data for improved regression

    vanderschaarlab/TRIAGE’s past year of commit activity
    Jupyter Notebook 2 Apache-2.0 3 0 0 Updated Nov 25, 2024
  • Datagnosis Public

    A Data-Centric library providing a unified interface for state-of-the-art methods for hardness characterisation of data points.

    vanderschaarlab/Datagnosis’s past year of commit activity
    Jupyter Notebook 23 Apache-2.0 2 1 0 Updated Nov 21, 2024
  • HDTwinGen Public Forked from samholt/HDTwinGen
    vanderschaarlab/HDTwinGen’s past year of commit activity
    Python 0 MIT 2 0 0 Updated Nov 10, 2024
  • NeuralLaplace Public Forked from samholt/NeuralLaplace

    Differentiable Laplace Reconstructions for modelling any time observation with O(1) complexity.

    vanderschaarlab/NeuralLaplace’s past year of commit activity
    Python 3 MIT 11 0 0 Updated Nov 2, 2024
  • POCA Public Forked from jumpynitro/POCA
    vanderschaarlab/POCA’s past year of commit activity
    Python 0 1 0 0 Updated Oct 31, 2024
  • medkit-learn Public Forked from XanderJC/medkit-learn

    The Medkit-Learn(ing) Environment. An open-source library for offline sequential decision making with a focus on medicine.

    vanderschaarlab/medkit-learn’s past year of commit activity
    Python 1 1 0 0 Updated Oct 2, 2024
View all repositories