Causal Feature

Causal feature research aims to identify the variables truly driving an outcome, disentangling them from spurious correlations. Current work focuses on developing methods to discover these features within various data modalities (text, images, graphs) using techniques like causal discovery algorithms, generative models, and contrastive learning, often incorporating meta-learning or backdoor adjustment strategies. This research is crucial for improving the robustness, generalizability, and interpretability of machine learning models across diverse domains, impacting fields ranging from healthcare and climate science to natural language processing.

Papers

July 7, 2023

Discovering Variable Binding Circuitry with Desiderata
Xander Davies, Max Nadeau, Nikhil Prakash, Tamar Rott Shaham, David Bau
Language Model Computation Method Variable Model Causal Feature Causal Mediation Analysis Model Documentation

July 1, 2023

Automatic Counterfactual Augmentation for Robust Text Classification Based on Word-Group Search
Rui Song, Fausto Giunchiglia, Yingji Li, Hao Xu
Shortcut Learning Causal Feature Domain Text Classification Counterfactual Augmentation Robust Text Classification

June 18, 2023

Can predictive models be used for causal inference?
Maximilian Pichler, Florian Hartig
Causal Inference Predictive Model Causal Learning Supervised Machine Learning Causal Feature Independent Variable Collinearity

June 12, 2023

DRCFS: Doubly Robust Causal Feature Selection
Francesco Quinzan, Ashkan Soleymani, Patrick Jaillet, Cristian R. Rojas, Stefan Bauer
Synthetic Data Feature Selection Causal Feature High Dimensional Problem

April 11, 2023

Selecting Robust Features for Machine Learning Applications using Multidata Causal Discovery
Saranya Ganesh S., Tom Beucler, Frederick Iat-Hin Tam, Milton S. Gomez, Jakob Runge, Andreas Gerhardus
Feature Selection Causal Discovery Machine Learning Application Causal Feature

March 29, 2023

Three-way causal attribute partial order structure analysis
Xue Zaifa, Lu Huibin, Zhang Tao, Li Tao, Lu Xin
Causal Relationship Causal Feature Three Way Partial Order

March 2, 2023

Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression
Junho Kim, Byung-Kwan Lee, Yong Man Ro
Adversarial Example Adversarial Robustness Instrumental Variable Causal Feature Causal Intervention Robust Network Adversarial Prediction

February 23, 2023

Rank-Based Causal Discovery for Post-Nonlinear Models
Grigor Keropyan, David Strieder, Mathias Drton
Causal Model Causal Relationship Structural Causal Model Nonlinear Model Causal Feature

February 18, 2023

Improving the Out-Of-Distribution Generalization Capability of Language Models: Counterfactually-Augmented Data is not Enough
Caoyun Fan, Wenqing Chen, Jidong Tian, Yitian Li, Hao He, Yaohui Jin
Language Model Natural Language Inference Distribution Generalization Causal Feature

January 29, 2023

On Learning Necessary and Sufficient Causal Graphs
Hengrui Cai, Yixin Wang, Michael Jordan, Rui Song
LeArning Abstract Causal Graph Causal Structure Learning Causal Feature

November 29, 2022

PatchMix Augmentation to Identify Causal Features in Few-shot Learning
Chengming Xu, Chen Liu, Xinwei Sun, Siqian Yang, Yabiao Wang, Chengjie Wang, Yanwei Fu
Shot Learning Causal Feature Mixing Data Augmentation

November 12, 2022

Actionable Recourse via GANs for Mobile Health
Jennifer Chien, Anna Guitart, Ana Fernandez del Rio, Africa Perianez, Lauren Bellhouse
GAN Model High Quality Counterfactuals Counterfactual Reasoning Mobile Health Causal Feature Robust Recourse Adaptive Intervention

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

July 8, 2022

MACFE: A Meta-learning and Causality Based Feature Engineering Framework
Ivan Reyes-Amezcua, Daniel Flores-Araiza, Gilberto Ochoa-Ruiz, Andres Mendez-Vazquez, Eduardo Rodriguez-Tello
Meta Learning Feature Selection Model Performance Feature Engineering Causal Feature

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 Feature Invariant Causal Explicitly Mentioned Causal Fact Causal Invariance

February 22, 2022

Automatically Generating Counterfactuals for Relation Classification
Mi Zhang, Tieyun Qian, Ting Zhang
Semantic Relation Causal Feature Relation Classification

December 30, 2021

Causal Attention for Interpretable and Generalizable Graph Classification
Yongduo Sui, Xiang Wang, Jiancan Wu, Min Lin, Xiangnan He, Tat-Seng Chua
Graph Classification Causal Effect Estimation Interpretable Way Causal Feature Causal Attention

November 26, 2021

Confounder Identification-free Causal Visual Feature Learning
Xin Li, Zhizheng Zhang, Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Xin Jin, Zhibo Chen
Causal Learning Causal Feature Text Based Confounders

November 3, 2021

SERC: Syntactic and Semantic Sequence based Event Relation Classification
Kritika Venkatachalam, Raghava Mutharaju, Sumit Bhatia
LSTM Network Textual Entailment Causal Relation Causal Feature Event Relation Extraction Causal Categorization Word Sequence