Causal Learning Algorithm

Causal learning algorithms aim to discover cause-and-effect relationships from data, moving beyond simple correlation analysis. Current research focuses on developing algorithms that handle high-dimensional data, decentralized datasets (federated learning), and multimodal information, often employing techniques like directed acyclic graphs (DAGs) and incorporating elements of deep learning. These advancements are crucial for improving the robustness and interpretability of machine learning models across diverse scientific fields and practical applications, such as vulnerability detection and reinforcement learning policy analysis.

Papers

December 9, 2023

October 27, 2023

Causal disentanglement of multimodal data
Elise Walker, Jonas A. Actor, Carianne Martinez, Nathaniel Trask
Multimodal Data Causal Representation Learning Causal Representation Causal Disentanglement Interpretable Causal Causal Learning Algorithm

October 12, 2023

Towards Causal Deep Learning for Vulnerability Detection
Md Mahbubur Rahman, Ira Ceka, Chengzhi Mao, Saikat Chakraborty, Baishakhi Ray, Wei Le
Native Robustness Vulnerability Detection Causal Learning Causal Approach Causal Deep Learning Causal Learning Algorithm

April 16, 2022

FedCau: A Proactive Stop Policy for Communication and Computation Efficient Federated Learning
Afsaneh Mahmoudi, Hossein S. Ghadikolaei, José Mairton Barros Da Silva Júnior, Carlo Fischione
Federated Learning Timely Communication Early Stopping Communication Cost Time Division Multiple Access Causal Learning Algorithm

February 7, 2022

Evaluation Methods and Measures for Causal Learning Algorithms
Lu Cheng, Ruocheng Guo, Raha Moraffah, Paras Sheth, K. Selcuk Candan, Huan Liu
Evaluation Method Causal Learning New Measure Causal Machine Learning Causality Based Learning Causal Learning Algorithm

November 16, 2021

Causal policy ranking
Daniel McNamee, Hana Chockler
Reinforcement Learning Causal Effect Counterfactual Reasoning Causal Learning Algorithm