Causal Interventional Regularizer

Causal interventional regularization aims to improve the robustness and generalizability of machine learning models by explicitly addressing the influence of confounding variables and spurious correlations. Current research focuses on developing methods to identify and mitigate these influences, often employing structural causal models and incorporating regularization terms into various model architectures, including deep learning models and multivariate analysis techniques. This approach is significant because it enhances the reliability and trustworthiness of machine learning predictions, particularly in scenarios with out-of-distribution data or noisy observations, leading to improved performance in diverse applications such as target recognition and recommendation systems.

Papers

October 16, 2024

Causally-Aware Unsupervised Feature Selection Learning
Zongxin Shen, Yanyong Huang, Minbo Ma, Tianrui Li
Feature Selection Causal Feature Unsupervised Feature Selection Causal Interventional Regularizer

July 19, 2024

On the Causal Sufficiency and Necessity of Multi-Modal Representation Learning
Jingyao Wang, Wenwen Qiang, Jiangmeng Li, Lingyu Si, Changwen Zheng, Bing Su
Community Need Multi Modal Learning Causal Representation Multi Modal Representation Learning Causal Attribution Causal Interventional Regularizer

March 4, 2024

Improving generalisation via anchor multivariate analysis
Homer Durand, Gherardo Varando, Nathan Mankovich, Gustau Camps-Valls
Strong Generalization Causal Inference Anchor Graph Proxy Based Loss Causal Interventional Regularizer

August 30, 2023

Background Debiased SAR Target Recognition via Causal Interventional Regularizer
Hongwei Dong, Fangzhou Han, Lingyu Si, Wenwen Qiang, Lamei Zhang
Synthetic Aperture Radar Target Recognition Causal Interventional Regularizer

June 19, 2023

Causal Effect Regularization: Automated Detection and Removal of Spurious Attributes
Abhinav Kumar, Amit Deshpande, Amit Sharma
Simple Classifier Automatic Detection Active Removal Spurious Feature Learned Model Causal Interventional Regularizer

February 20, 2023

Neural Algorithmic Reasoning with Causal Regularisation
Beatrice Bevilacqua, Kyriacos Nikiforou, Borja Ibarz, Ioana Bica, Michela Paganini, Charles Blundell, Jovana Mitrovic, Petar Veličković
Reasoning Capability Neural Algorithmic Reasoning Neural Reasoning Causal Interventional Regularizer

October 7, 2022

Using Interventions to Improve Out-of-Distribution Generalization of Text-Matching Recommendation Systems
Parikshit Bansal, Yashoteja Prabhu, Emre Kiciman, Amit Sharma
Distribution Generalization Recommendation Task Health Intervention Item Based Collaborative Filtering Item Relevance Text Aware Causal Interventional Regularizer

December 6, 2021

Deconfounding Temporal Autoencoder: Estimating Treatment Effects over Time Using Noisy Proxies
Milan Kuzmanovic, Tobias Hatt, Stefan Feuerriegel
Time Matter Treatment Effect Text Based Confounders Proxy Dataset Causal Interventional Regularizer Temporal Autoencoder