Causal Dynamic Learning

Causal dynamic learning focuses on building models that predict system behavior by explicitly representing causal relationships between variables, improving robustness and generalization compared to traditional methods. Current research emphasizes developing models that handle complex, high-dimensional data (e.g., fMRI time series, object-oriented environments, time series data) and account for factors like non-linearity, non-stationarity, and missing data, often employing techniques like Bayesian networks, state-space models, and deep learning architectures (e.g., Graph Neural Networks, Causal Neural Networks). This approach is proving valuable in diverse fields, enhancing reinforcement learning, improving the accuracy and generalizability of visual recognition, and enabling more efficient and robust analysis of complex systems like the brain.

Papers

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

June 5, 2024

Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning
Inwoo Hwang, Yunhyeok Kwak, Suhyung Choi, Byoung-Tak Zhang, Sanghack Lee
Reinforcement Learning Native Robustness Causal Structure Quantization Operator Causal Dynamic Learning Fine Grained Causal

May 21, 2024

Learning Causal Dynamics Models in Object-Oriented Environments
Zhongwei Yu, Jingqing Ruan, Dengpeng Xing
Reinforcement Learning Causal Discovery Object Oriented Causal System Causal Dynamic Learning

April 2, 2024

Causality-based Transfer of Driving Scenarios to Unseen Intersections
Christoph Glasmacher, Michael Schuldes, Sleiman El Masri, Lutz Eckstein
Causal Pattern Bayesian Network Multi Scenario Scenario Based Testing Vehicle Behavior Causal Dynamic Learning

April 1, 2024

TS-CausalNN: Learning Temporal Causal Relations from Non-linear Non-stationary Time Series Data
Omar Faruque, Sahara Ali, Xue Zheng, Jianwu Wang
Time Series Causal Relation Causal Discovery Method Neural Causal Model Causal Dynamic Learning

February 23, 2024

Learning Cyclic Causal Models from Incomplete Data
Muralikrishnna G. Sethuraman, Faramarz Fekri
Causal Graph Causal Learning Incomplete Data Causal Discovery Algorithm Causal Dynamic Learning

June 27, 2022

Causal Dynamics Learning for Task-Independent State Abstraction
Zizhao Wang, Xuesu Xiao, Zifan Xu, Yuke Zhu, Peter Stone
Model Based Reinforcement Learning Learned Dynamic State Abstraction Causal System Causal Dynamic Learning

April 26, 2022

Causal Transportability for Visual Recognition
Chengzhi Mao, Kevin Xia, James Wang, Hao Wang, Junfeng Yang, Elias Bareinboim, Carl Vondrick
Image Classification Visual Representation Causal Graph Distribution Generalization Visual Recognition Causal Dynamic Learning Causal Invariance