Causal Influence

Causal influence research aims to identify and quantify the true cause-and-effect relationships underlying observed correlations, moving beyond mere statistical associations. Current efforts focus on developing methods to disentangle causal effects from confounding variables using techniques like Bayesian networks, linear state-space models, and graph neural networks, often within the context of specific applications such as fMRI analysis, machine learning robustness, and reinforcement learning. This work is significant because accurately identifying causal relationships improves the reliability and generalizability of models across diverse domains, leading to more robust predictions and better-informed decision-making in fields ranging from healthcare to artificial intelligence.

Papers

October 25, 2024

Unified Causality Analysis Based on the Degrees of Freedom
András Telcs, Marcell T. Kurbucz, Antal Jakovác
Causal Relationship Latent Confounders Underlying Causal Different Degree Freedom Matter Causal Influence

September 26, 2024

Causality-based Subject and Task Fingerprints using fMRI Time-series Data
Dachuan Song, Li Shen, Duy Duong-Tran, Xuan Wang
fMRI Time Series Causal Influence Causal Dynamic Learning

August 28, 2024

Certified Causal Defense with Generalizable Robustness
Yiran Qiao, Yu Yin, Chen Chen, Jing Ma
Adversarial Attack Adversarial Perturbation Adversarial DEfense Certified Defense Causal Influence

August 16, 2024

Bayesian Network Modeling of Causal Influence within Cognitive Domains and Clinical Dementia Severity Ratings for Western and Indian Cohorts
Wupadrasta Santosh Kumar, Sayali Rajendra Bhutare, Neelam Sinha, Thomas Gregor Issac
Alzheimer'S Disease Causal Relationship Bayesian Network Cognitive Learning Longitudinal Study Disease Neuroimaging Initiative Expert Delineated Cohort Causal Influence

May 2, 2024

Causal Influence in Federated Edge Inference
Mert Kayaalp, Yunus Inan, Visa Koivunen, Ali H. Sayed
Scientific Inference Agent Behavior Heterogeneous Agent Federated Edge Learning Causal Influence Local Inference

February 15, 2024

Do causal predictors generalize better to new domains?
Vivian Y. Nastl, Moritz Hardt
Causal Pattern Causal Feature Causal Prediction Causal Influence New Domain

January 30, 2024

CaMU: Disentangling Causal Effects in Deep Model Unlearning
Shaofei Shen, Chenhao Zhang, Alina Bialkowski, Weitong Chen, Miao Xu
Causal Effect Machine Unlearning Unlearning Framework Harmful Unlearning Causal Influence

September 19, 2023

Exploiting Causality Signals in Medical Images: A Pilot Study with Empirical Results
Gianluca Carloni, Sara Colantonio
Medical Image Empirical Study Pilot Study Convolutional Backbone Causality Extraction Prostate Magnetic Resonance Causal Influence Causality Detection Visual Causality Discovery

September 14, 2023

Causal Entropy and Information Gain for Measuring Causal Control
Francisco Nunes Ferreira Quialheiro Simoes, Mehdi Dastani, Thijs van Ommen
Causal Structure Information Gain Interpretable Causal Causal Entropy Causal Influence

August 27, 2023

Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP
Vedant Palit, Rohan Pandey, Aryaman Arora, Paul Pu Liang
Mechanistic Interpretability Causal Influence Causal Intervention Module Bit Level Information Preserving

November 8, 2022

Much Easier Said Than Done: Falsifying the Causal Relevance of Linear Decoding Methods
Lucas Hayne, Abhijit Suresh, Hunar Jain, Rahul Kumar, R. McKell Carter
Linear Classifier Selective Engagement Decoding Method Causal Influence Selective Neuron Additive Decoder

October 24, 2022

Causal Explanation for Reinforcement Learning: Quantifying State and Temporal Importance
Xiaoxiao Wang, Fanyu Meng, Xin Liu, Zhaodan Kong, Xin Chen
Reinforcement Learning High Explainability Internal State Causal Direction Causal Explanation Association Test Causal Influence

February 4, 2022

Correcting Confounding via Random Selection of Background Variables
You-Lin Chen, Lenon Minorics, Dominik Janzing
Causal Relationship Background Generation Confounding Bias Causal Attribution Random Selection Causal Influence Causal Insight