Actual Causality

Actual causality aims to identify the specific events that truly caused a particular outcome, going beyond simple correlations. Current research focuses on developing algorithms and models, such as those based on transformer networks, answer set programming, and structural causal models, to accurately infer actual causes from observational or interventional data, even in complex, high-dimensional systems. This work is crucial for improving the reliability and explainability of AI systems, enhancing the robustness of cyber-physical systems, and providing a more nuanced understanding of causality in various scientific domains, including physics and legal contexts. The ability to precisely determine causality has significant implications for fields ranging from machine learning and AI safety to scientific modeling and legal responsibility.

Papers

October 11, 2024

DiffPO: A causal diffusion model for learning distributions of potential outcomes
Yuchen Ma, Valentyn Melnychuk, Jonas Schweisthal, Stefan Feuerriegel
Causal Inference Multiple Outcome Conditional Denoising Diffusion Actual Causality

July 10, 2024

Teaching Transformers Causal Reasoning through Axiomatic Training
Aniket Vashishtha, Abhinav Kumar, Abbavaram Gowtham Reddy, Vineeth N Balasubramanian, Amit Sharma
Causal Transformer Training Paradigm Actual Causality Causal Theory

April 16, 2024

Automated Discovery of Functional Actual Causes in Complex Environments
Caleb Chuck, Sankaran Vaidyanathan, Stephen Giguere, Amy Zhang, David Jensen, Scott Niekum
Reinforcement Learning Complex Environment Actual Cause Cause Effect Underlying Causal Automatic Discovery Actual Causality

September 21, 2023

Extracting Physical Causality from Measurements to Detect and Localize False Data Injection Attacks
Shengyang Wu, Jingyu Wang, Dongyuan Shi
Cyber Physical Actual Causality Internal Measurement False Data Injection Attack Data Injection Attack

July 31, 2023

Attribution-Scores in Data Management and Explainable Machine Learning
Leopoldo Bertossi
Machine Learning Classification Model Explainable Machine Learning Attribution Score Data Management Actual Causality

July 11, 2023

Causal Kripke Models
Yiwen Ding, Krishna Manoorkar, Apostolos Tzimoulis, Ruoding Wang, Xiaolong Wang
Causal Model Causal Pattern Actual Causality Kripke Model

June 6, 2023

Embracing Background Knowledge in the Analysis of Actual Causality: An Answer Set Programming Approach
Michael Gelfond, Jorge Fandinno, Evgenii Balai
General Analysis Answer Set Programming Knowledge Representation Actual Cause Background Knowledge Causal Knowledge Actual Causality

May 24, 2023

"What if?" in Probabilistic Logic Programming
Rafael Kiesel, Kilian Rückschloß, Felix Weitkämper
Counterfactual Reasoning Logic Programming Logic Program Counterfactual Query Actual Causality

April 6, 2023

Causal Repair of Learning-enabled Cyber-physical Systems
Pengyuan Lu, Ivan Ruchkin, Matthew Cleaveland, Oleg Sokolsky, Insup Lee
Causal Model Cyber Physical System Actual Causality

December 18, 2022

A Layered Architecture for Universal Causality
Sridhar Mahadevan
Multi Layer Causal Structure Causal Model Category Theory Categorical Feature Actual Causality Causal Strength

October 11, 2022

A Causal Analysis of Harm
Sander Beckers, Hana Chockler, Joseph Y. Halpern
Causal Model Causal Pattern Causal Analysis Potential Harm Actual Causality

October 10, 2022

Mining Causality from Continuous-time Dynamics Models: An Application to Tsunami Forecasting
Fan Wu, Sanghyun Hong, Donsub Rim, Noseong Park, Kookjin Lee
Application Proficiency Causal Structure Continuous Time Model Actual Causality Continuous Time Dynamic Tsunami Scenario

July 6, 2022

On The Universality of Diagrams for Causal Inference and The Causal Reproducing Property
Sridhar Mahadevan
Causal Inference K$ Universality Fundamental Diagram Actual Causality

May 5, 2022

Action Languages Based Actual Causality for Computational Ethics: a Sound and Complete Implementation in ASP
Camilo Sarmiento, Gauvain Bourgne, Katsumi Inoue, Daniele Cavalli, Jean-Gabriel Ganascia
Causal Pattern Logic Programming Cause Effect Implementation Detail Actual Causality Machine Ethic Language Action

April 1, 2022

Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes
Stelios Triantafyllou, Adish Singla, Goran Radanovic
Markov Decision Process C POMDPs Decentralized Manner Multi Agent Sequential Decision Actual Causality Responsibility Attribution

March 14, 2022

Respecting causality is all you need for training physics-informed neural networks
Sifan Wang, Shyam Sankaran, Paris Perdikaris
Physic Informed Neural Network Causal Pattern Chaotic Regime Stratified Turbulence Actual Causality Chaotic Lorenz

December 16, 2021

Causal Modeling With Infinitely Many Variables
Spencer Peters, Joseph Y. Halpern
Causal Model Causal Pattern Structural Equation Actual Causality Feature Impact Balance Sem