Causal Explanation

Causal explanation in machine learning aims to move beyond simple correlations, providing understandable and actionable reasons for model predictions. Current research focuses on developing methods that identify causal relationships within data, often leveraging techniques from causal inference, graph neural networks, and large language models to generate explanations in various forms, including counterfactuals and structural causal models. This work is crucial for building trust in AI systems, improving model fairness and robustness, and facilitating effective human-AI collaboration across diverse applications like healthcare, industrial maintenance, and autonomous driving.

Papers

November 13, 2024

Causal Explanations for Image Classifiers
Hana Chockler, David A. Kelly, Daniel Kroening, Youcheng Sun
Line by Line Explanation Average Approximation Image Classifier Causal Explanation

October 7, 2024

Neural Networks Decoded: Targeted and Robust Analysis of Neural Network Decisions via Causal Explanations and Reasoning
Alec F. Diallo, Vaishak Belle, Paul Patras
Deep Learning Complex Reasoning Causal Inference Causal Graph Interpretability Method Causal Explanation Causal System Neural Network Decoder

September 10, 2024

Causal Analysis of Shapley Values: Conditional vs. Marginal
Ilya Rozenfeld
Shapley Value Causal Analysis Conditional Reasoning Causal Explanation Conditional Model

July 30, 2024

Industrial-Grade Smart Troubleshooting through Causal Technical Language Processing: a Proof of Concept
Alexandre Trilla, Ossee Yiboe, Nenad Mijatovic, Jordi Vitrià
Causal Relationship High Impact Concept Causal Learning Predictive Maintenance Partial Proof Causal Approach Causal Explanation Causal Machine Intelligent Fault Diagnosis

July 12, 2024

Graph Neural Network Causal Explanation via Neural Causal Models
Arman Behnam, Binghui Wang
Graph Neural Network Causal Structure Structural Causal Model Causal Explanation Neural Causal Model GNN Explainers

May 29, 2024

SIG: Efficient Self-Interpretable Graph Neural Network for Continuous-time Dynamic Graphs
Lanting Fang, Yulian Yang, Kai Wang, Shanshan Feng, Kaiyu Feng, Jie Gui, Shuliang Wang, Yew-Soon Ong
Causal Inference Dynamic Graph Causal Explanation Continuous Time Dynamic Graph Interpretable Graph Neural Network

March 11, 2024

Narrating Causal Graphs with Large Language Models
Atharva Phatak, Vijay K. Mago, Ameeta Agrawal, Aravind Inbasekaran, Philippe J. Giabbanelli
Knowledge Graph Causal Graph Causal Explanation

January 16, 2024

DiConStruct: Causal Concept-based Explanations through Black-Box Distillation
Ricardo Moreira, Jacopo Bono, Mário Cardoso, Pedro Saleiro, Mário A. T. Figueiredo, Pedro Bizarro
Knowledge Distillation Line by Line Explanation Local Explanation Concept Based Causal Event Causal Explanation Structural Construct

November 19, 2023

Using Causal Threads to Explain Changes in a Dynamic System
Robert B. Allen
Line by Line Explanation Dynamical System Temporal Knowledge Graph Pre Change Information Causal Explanation Causal Thread

October 31, 2023

Causal Interpretation of Self-Attention in Pre-Trained Transformers
Raanan Y. Rohekar, Yaniv Gurwicz, Shami Nisimov
Self Attention Causal Structure Pre Trained Transformer Causal Explanation Causal Interpretation Zero Shot Causal

October 1, 2023

Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals
Yair Gat, Nitay Calderon, Amir Feder, Alexander Chapanin, Amit Sharma, Roi Reichart
Large Language Model Model Agnostic Faithful Explanation Causal Explanation Black Box Language Model Model Agnostic Explanation Effective Explanation

April 30, 2023

Causalainer: Causal Explainer for Automatic Video Summarization
Jia-Hong Huang, Chao-Han Huck Yang, Pin-Yu Chen, Min-Hung Chen, Marcel Worring
Video Summarization Causal Explanation Causal Relation Extraction

February 21, 2023

Causal Explanations for Sequential Decision-Making in Multi-Agent Systems
Balint Gyevnar, Cheng Wang, Christopher G. Lucas, Shay B. Cohen, Stefano V. Albrecht
Multi Agent System Sequential Decision Causal Explanation Multi Agent Sequential Decision Trustworthy Autonomy

December 5, 2022

This changes to that : Combining causal and non-causal explanations to generate disease progression in capsule endoscopy
Anuja Vats, Ahmed Mohammed, Marius Pedersen, Nirmalie Wiratunga
Line by Line Explanation Saliency Map Causal Direction Pre Change Information Causal Explanation Capsule Endoscopy Explanation Representation Format

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

October 16, 2022

Explainable Causal Analysis of Mental Health on Social Media Data
Chandni Saxena, Muskan Garg, Gunjan Ansari
Mental Health Social Medium Data Multi Class Classification Causal Explanation Causal Categorization Explainable Causal

October 7, 2022

CLEAR: Causal Explanations from Attention in Neural Recommenders
Shami Nisimov, Raanan Y. Rohekar, Yaniv Gurwicz, Guy Koren, Gal Novik
Human Attention Counterfactual Explanation Causal Graph Latent Confounders Causal Explanation Class Enhanced Attentive Response Session Graph

June 30, 2022

Causal Machine Learning: A Survey and Open Problems
Jean Kaddour, Aengus Lynch, Qi Liu, Matt J. Kusner, Ricardo Silva
Timely Survey Open Problem Causal Machine Learning Causal Explanation Causal Machine Causal Reinforcement Learning Causal Generative

June 17, 2022

A Human-Centric Method for Generating Causal Explanations in Natural Language for Autonomous Vehicle Motion Planning
Balint Gyevnar, Massimiliano Tamborski, Cheng Wang, Christopher G. Lucas, Shay B. Cohen, Stefano V. Albrecht
Autonomous Driving Autonomous Vehicle Natural Language Explanation Generation Human Centered Human Centric Causal Explanation Vehicle Motion Planning

June 1, 2022

Why Did This Model Forecast This Future? Closed-Form Temporal Saliency Towards Causal Explanations of Probabilistic Forecasts
Chirag Raman, Hayley Hung, Marco Loog
Future Reasoning Probabilistic Forecast Human Saliency Saliency Detection Causal Explanation Temporal Saliency