Invariant Causal Feature

Invariant causal feature learning aims to develop machine learning models robust to distributional shifts by identifying and leveraging features causally related to the target variable, while ignoring spurious correlations. Current research focuses on disentangling causal and non-causal features using causal inference techniques, often incorporating contrastive learning, intervention methods, and prototype-based approaches within various model architectures. This research is significant because it promises improved generalization performance in real-world applications where data distributions are inherently variable, such as in autonomous driving, remote sensing, and drug discovery.

Papers

June 10, 2024

Causality-inspired Latent Feature Augmentation for Single Domain Generalization
Jian Xu, Chaojie Ji, Yankai Cao, Ye Li, Ruxin Wang
Single Domain Generalization Multi Source Domain Generalization Invariant Causal Feature

March 6, 2024

Causal Prototype-inspired Contrast Adaptation for Unsupervised Domain Adaptive Semantic Segmentation of High-resolution Remote Sensing Imagery
Jingru Zhu, Ya Guo, Geng Sun, Liang Hong, Jie Chen
Contrastive Learning Remote Sensing Semantic Segmentation Model Causal Event Domain Adaptive Semantic Segmentation Causal Feature Invariant Causal Feature Contrast Adaptation

February 20, 2024

Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition
Yuke Li, Guangyi Chen, Ben Abramowitz, Stefano Anzellott, Donglai Wei
Action Recognition Causal Learning Shot Action Recognition Temporal Shift Invariant Causal Feature

December 15, 2023

Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach
Ziliang Chen, Yongsen Zheng, Zhao-Rong Lai, Quanlong Guan, Liang Lin
Medical Diagnosis Invariant Representation Causal Feature Causal Approach Invariant Causal Feature

October 10, 2023

Unlock the Potential of Counterfactually-Augmented Data in Out-Of-Distribution Generalization
Caoyun Fan, Wenqing Chen, Jidong Tian, Yitian Li, Hao He, Yaohui Jin
Full Potential Distribution Generalization Causal Feature Unlocking Insight Invariant Causal Feature

July 11, 2023

CILF:Causality Inspired Learning Framework for Out-of-Distribution Vehicle Trajectory Prediction
Shengyi Li, Qifan Xue, Yezhuo Zhang, Xuanpeng Li
Vehicle Trajectory Prediction Class Incremental Continual Learning Invariant Causal Feature Graph Out of Distribution Causality Based Learning

April 5, 2023

A step towards the applicability of algorithms based on invariant causal learning on observational data
Borja Guerrero Santillan
Practical Algorithm Causal Inference Causal Discovery Observational Data Causal Discovery Method Sample STEP Applicability Study Optimal Prediction Invariant Causal Invariant Causal Feature

March 12, 2023

RotoGBML: Towards Out-of-Distribution Generalization for Gradient-Based Meta-Learning
Min Zhang, Zifeng Zhuang, Zhitao Wang, Donglin Wang, Wenbin Li
Distribution Generalization Meta Training Gradient Based Meta Learning Generalization Problem Invariant Causal Feature Task Gradient

September 29, 2022

Contrastive Unsupervised Learning of World Model with Invariant Causal Features
Rudra P. K. Poudel, Harit Pandya, Roberto Cipolla
World Model Model Free Reinforcement Learning unsupeRvised Contrastive Learning Causal Feature Invariant Causal Feature

August 22, 2022

GCISG: Guided Causal Invariant Learning for Improved Syn-to-real Generalization
Gilhyun Nam, Gyeongjae Choi, Kyungmin Lee
Synthetic Dataset Synthetic to Real Invariant Causal Feature

March 29, 2022

Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data
Siyuan Guo, Viktor Tóth, Bernhard Schölkopf, Ferenc Huszár
Causal Discovery Person Identification Causal Structure Conditional Independence Causal Discovery Method Causal Discovery Algorithm Invariant Causal Feature De Finetti

March 22, 2022

Out-of-distribution Generalization with Causal Invariant Transformations
Ruoyu Wang, Mingyang Yi, Zhitang Chen, Shengyu Zhu
Distribution Generalization Causal Feature Invariant Causal Invariant Causal Feature Explicitly Mentioned Causal Fact Causal Invariance

February 11, 2022

Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs
Yongqiang Chen, Yonggang Zhang, Yatao Bian, Han Yang, Kaili Ma, Binghui Xie, Tongliang Liu, Bo Han, James Cheng
Graph Drawing Distribution Generalization Causal Model Alpha Invariance Causal Representation Learning Model Invariance Invariant Causal Feature

Invariant Causal Feature

Papers

Causality-inspired Latent Feature Augmentation for Single Domain Generalization

Causal Prototype-inspired Contrast Adaptation for Unsupervised Domain Adaptive Semantic Segmentation of High-resolution Remote Sensing Imagery

Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition

Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach

Unlock the Potential of Counterfactually-Augmented Data in Out-Of-Distribution Generalization

CILF:Causality Inspired Learning Framework for Out-of-Distribution Vehicle Trajectory Prediction

A step towards the applicability of algorithms based on invariant causal learning on observational data

RotoGBML: Towards Out-of-Distribution Generalization for Gradient-Based Meta-Learning

Contrastive Unsupervised Learning of World Model with Invariant Causal Features

GCISG: Guided Causal Invariant Learning for Improved Syn-to-real Generalization

Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data

Out-of-distribution Generalization with Causal Invariant Transformations

Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs