Latent Causal

Latent causal representation learning aims to uncover hidden causal variables and their relationships from high-dimensional observational data, enabling causal inference and improved prediction in various domains. Current research focuses on developing methods that address challenges like non-linearity, partial observability, and unknown interventions, often employing techniques such as autoencoders, variational inference, and graph neural networks to learn disentangled representations and identify causal structures. These advancements are significant for improving the interpretability and robustness of machine learning models, and have implications across diverse fields including healthcare, ecology, and reinforcement learning.

Papers

December 18, 2023

A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables
Xinshuai Dong, Biwei Huang, Ignavier Ng, Xiangchen Song, Yujia Zheng, Songyao Jin, Roberto Legaspi, Peter Spirtes, Kun Zhang
Causal Discovery Causal Discovery Method Latent Causal Causal Network

December 13, 2023

Reconciling Shared versus Context-Specific Information in a Neural Network Model of Latent Causes
Qihong Lu, Tan T. Nguyen, Qiong Zhang, Uri Hasson, Thomas L. Griffiths, Jeffrey M. Zacks, Samuel J. Gershman, Kenneth A. Norman
Context Learning Context Information Neural Network Model LLM Inference Latent Causal Sharing Matter Contextual Structure Common Cause

December 6, 2023

Invariance & Causal Representation Learning: Prospects and Limitations
Simon Bing, Jonas Wahl, Urmi Ninad, Jakob Runge
Causal Model Fundamental Limitation Alpha Invariance Causal Representation Learning Visionary ProSpect Latent Causal Causal Representation Causal Variable

November 5, 2023

Identifying Linearly-Mixed Causal Representations from Multi-Node Interventions
Simon Bing, Urmi Ninad, Jonas Wahl, Jakob Runge
Causal Representation Learning Latent Causal Ground Truth Causal Node Intervention

October 28, 2023

Temporally Disentangled Representation Learning under Unknown Nonstationarity
Xiangchen Song, Weiran Yao, Yewen Fan, Xinshuai Dong, Guangyi Chen, Juan Carlos Niebles, Eric Xing, Kun Zhang
Causal Representation Learning Latent Causal Non Stationarity

September 30, 2023

Interpretable Imitation Learning with Dynamic Causal Relations
Tianxiang Zhao, Wenchao Yu, Suhang Wang, Lu Wang, Xiang Zhang, Yuncong Chen, Yanchi Liu, Wei Cheng, Haifeng Chen
Imitation Learning Causal Graph Causal Relation Latent Causal

August 13, 2023

Generalized Independent Noise Condition for Estimating Causal Structure with Latent Variables
Feng Xie, Biwei Huang, Zhengming Chen, Ruichu Cai, Clark Glymour, Zhi Geng, Kun Zhang
Latent Variable Causal Structure Latent Causal Causal Ordering Linear Non Gaussian Acyclic Model Dependent Noise

July 12, 2023

Identifiability Guarantees for Causal Disentanglement from Soft Interventions
Jiaqi Zhang, Chandler Squires, Kristjan Greenewald, Akash Srivastava, Karthikeyan Shanmugam, Caroline Uhler
Latent Causal Causal Variable Unobserved Variable Causal Disentanglement Partial Identifiability Soft Intervention

June 23, 2023

Prediction under Latent Subgroup Shifts with High-Dimensional Observations
William I. Walker, Arthur Gretton, Maneesh Sahani
Human Prediction High Dimensional Latent Causal Discrete Latent Latent Shift Subgroup Shift

June 20, 2023

Towards Characterizing Domain Counterfactuals For Invertible Latent Causal Models
Zeyu Zhou, Ruqi Bai, Sean Kulinski, Murat Kocaoglu, David I. Inouye
Latent Causal Counterfactual Estimation Counterfactual Query Counterfactual Sample Domain Counterfactual

June 5, 2023

Learning nonparametric latent causal graphs with unknown interventions
Yibo Jiang, Bryon Aragam
Latent Space Latent Causal Latent Structure Parametric Model Non Parametric Learning Unknown Intervention

June 2, 2023

Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms
Aneesh Komanduri, Yongkai Wu, Feng Chen, Xintao Wu
LeArning Abstract Disentanglement Capability Disentangled Representation General Principle Latent Causal Causal Variable Causal Disentanglement

June 1, 2023

Nonparametric Identifiability of Causal Representations from Unknown Interventions
Julius von Kügelgen, Michel Besserve, Liang Wendong, Luigi Gresele, Armin Kekić, Elias Bareinboim, David M. Blei, Bernhard Schölkopf
Causal Representation Learning Latent Causal Causal Representation Underlying Causal Unknown Intervention

May 26, 2023

Causal Component Analysis
Liang Wendong, Armin Kekić, Julius von Kügelgen, Simon Buchholz, Michel Besserve, Luigi Gresele, Bernhard Schölkopf
Causal Representation Learning Independent Component Analysis Latent Causal Independent Latent

March 11, 2023

Learning interpretable causal networks from very large datasets, application to 400,000 medical records of breast cancer patients
Marcel da Câmara Ribeiro-Dantas, Honghao Li, Vincent Cabeli, Louise Dupuis, Franck Simon, Liza Hettal, Anne-Sophie Hamy, Hervé Isambert
LeArning Abstract Causal Discovery Clinical Note Breast Cancer Causal Relation Latent Causal Large Datasets Causal Network Interpretable Causal

February 2, 2023

Unpaired Multi-Domain Causal Representation Learning
Nils Sturma, Chandler Squires, Mathias Drton, Caroline Uhler
Causal Graph Latent Variable Causal Representation Learning Latent Causal Causal Representation Unpaired Data

January 19, 2023

Score-based Causal Representation Learning with Interventions
Burak Varici, Emre Acarturk, Karthikeyan Shanmugam, Abhishek Kumar, Ali Tajer
Latent Variable Causal Representation Learning Latent Causal Health Intervention