Causal Disentanglement

Causal disentanglement aims to learn data representations where each component corresponds to an independent causal factor, rather than a statistical correlation. Current research focuses on developing algorithms, often based on variational autoencoders (VAEs) or graph neural networks, that can identify and separate these causal factors, even in the presence of confounding variables, using techniques like interventional data or self-supervised learning. This field is significant because disentangled representations improve model interpretability, robustness (e.g., to adversarial attacks), and generalization across different contexts, with applications ranging from recommendation systems and hate speech detection to biological modeling and fault diagnosis.

Papers

October 31, 2024

Identifiability Guarantees for Causal Disentanglement from Purely Observational Data
Ryan Welch, Jiaqi Zhang, Caroline Uhler
Disentanglement Capability Observational Data Causal Representation Causal Disentanglement Partial Identifiability Causal Hierarchy

September 9, 2024

Celcomen: spatial causal disentanglement for single-cell and tissue perturbation modeling
Stathis Megas, Daniel G. Chen, Krzysztof Polanski, Moshe Eliasof, Carola-Bibiane Schonlieb, Sarah A. Teichmann
Spatial Transcriptomics Turkish Text Causal Disentanglement Single Cell Data Genetic Network

July 5, 2024

Linear causal disentanglement via higher-order cumulants
Paula Leyes Carreno, Chiara Meroni, Anna Seigal
Latent Variable Linear Ordered Data Causal Representation Causal Disentanglement Order Cumulants

July 4, 2024

Collision Avoidance for Multiple UAVs in Unknown Scenarios with Causal Representation Disentanglement
Jiafan Zhuang, Zihao Xia, Gaofei Han, Boxi Wang, Wenji Li, Dongliang Wang, Zhifeng Hao, Ruichu Cai, Zhun Fan
Deep Reinforcement Learning Collision Avoidance Policy Learning Multi Scenario Multi UAV Causal Disentanglement

April 17, 2024

Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement
Paras Sheth, Tharindu Kumarage, Raha Moraffah, Aman Chadha, Huan Liu
Hate Speech Hate Speech Detection Content Moderation Causal Disentanglement Supervised CAusal Disentanglement

March 6, 2024

Causal Disentanglement for Regulating Social Influence Bias in Social Recommendation
Li Wang, Min Xu, Quangui Zhang, Yunxiao Shi, Qiang Wu
Causal Disentanglement Social Influence Social Recommendation Influence Graph

November 17, 2023

Concept-free Causal Disentanglement with Variational Graph Auto-Encoder
Jingyun Feng, Lin Zhang, Lili Yang
Causal Disentanglement Causal DAG Variational Graph Auto Meta Tree

November 11, 2023

SCADI: Self-supervised Causal Disentanglement in Latent Variable Models
Heejeong Nam
Causal Relationship Structural Causal Model Latent Variable Model Causal Disentanglement Supervised CAusal Disentanglement

October 27, 2023

Causal disentanglement of multimodal data
Elise Walker, Jonas A. Actor, Carianne Martinez, Nathaniel Trask
Multimodal Data Causal Representation Learning Causal Representation Causal Disentanglement Interpretable Causal Causal Learning Algorithm

October 26, 2023

C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder
Xiaoyu Liu, Jiaxin Yuan, Bang An, Yuancheng Xu, Yifan Yang, Furong Huang
Inductive Bias Disentanglement Capability Text Based Confounders Causal Disentanglement Generative Factor

September 13, 2023

Dynamic Causal Disentanglement Model for Dialogue Emotion Detection
Yuting Su, Yichen Wei, Weizhi Nie, Sicheng Zhao, Anan Liu
Emotion Detection Causal Disentanglement Dialogue Emotion

August 21, 2023

Measuring the Effect of Causal Disentanglement on the Adversarial Robustness of Neural Network Models
Preben M. Ness, Dusica Marijan, Sunanda Bose
Adversarial Attack Adversarial Robustness Mixed Effect Neural Network Model Causal Disentanglement Neural Causal Model Disentanglement Metric

August 6, 2023

Causal Disentanglement Hidden Markov Model for Fault Diagnosis
Rihao Chang, Yongtao Ma, Weizhi Nie, Jie Nie, An-an Liu
Causal Disentanglement

August 3, 2023

Causality Guided Disentanglement for Cross-Platform Hate Speech Detection
Paras Sheth, Tharindu Kumarage, Raha Moraffah, Aman Chadha, Huan Liu
Hate Speech Hate Speech Detection Causal Disentanglement

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 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

April 18, 2023

Causal Flow-based Variational Auto-Encoder for Disentangled Causal Representation Learning
Di Fan, Yannian Kou, Chuanhou Gao
Variational Autoencoder Variational Auto Causal Disentanglement Generative Factor Disentangled Causal

March 20, 2023

Approaching an unknown communication system by latent space exploration and causal inference
Gašper Beguš, Andrej Leban, Shane Gero
Latent Space Causal Inference Meaningful Representation Causal Disentanglement Unsupervised Generative Animal Communication

February 23, 2023

Causally Disentangled Generative Variational AutoEncoder
Seunghwan An, Kyungwoo Song, Jong-June Jeon
Variational Autoencoder Causal Disentanglement Generative Autoencoder Supervised Regularization

November 29, 2022

Linear Causal Disentanglement via Interventions
Chandler Squires, Anna Seigal, Salil Bhate, Caroline Uhler
Latent Variable Causal Model Latent Causal Health Intervention Causal Disentanglement Latent Linear

Causal Disentanglement

Papers

Identifiability Guarantees for Causal Disentanglement from Purely Observational Data

Celcomen: spatial causal disentanglement for single-cell and tissue perturbation modeling

Linear causal disentanglement via higher-order cumulants

Collision Avoidance for Multiple UAVs in Unknown Scenarios with Causal Representation Disentanglement

Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement

Causal Disentanglement for Regulating Social Influence Bias in Social Recommendation

Concept-free Causal Disentanglement with Variational Graph Auto-Encoder

SCADI: Self-supervised Causal Disentanglement in Latent Variable Models

Causal disentanglement of multimodal data

C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder

Dynamic Causal Disentanglement Model for Dialogue Emotion Detection

Measuring the Effect of Causal Disentanglement on the Adversarial Robustness of Neural Network Models

Causal Disentanglement Hidden Markov Model for Fault Diagnosis

Causality Guided Disentanglement for Cross-Platform Hate Speech Detection

Identifiability Guarantees for Causal Disentanglement from Soft Interventions

Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms

Causal Flow-based Variational Auto-Encoder for Disentangled Causal Representation Learning

Approaching an unknown communication system by latent space exploration and causal inference

Causally Disentangled Generative Variational AutoEncoder

Linear Causal Disentanglement via Interventions