Instance Level Causal

Instance-level causal inference aims to identify cause-and-effect relationships between individual events or instances within complex systems, moving beyond aggregate-level analyses. Current research focuses on developing novel algorithms, such as those based on Hawkes processes and self-attentive neural networks, to uncover these fine-grained causal structures from diverse data types, including event sequences and multi-instance learning settings. This detailed understanding of instance-level causality is crucial for improving decision-making in various domains, from optimizing resource allocation in power grids to enhancing the robustness of machine learning models.

Papers

May 28, 2024

Causal Contextual Bandits with Adaptive Context
Rahul Madhavan, Aurghya Maiti, Gaurav Sinha, Siddharth Barman
Regret Guarantee Causal Bandit Instance Level Causal

February 6, 2024

Learning Granger Causality from Instance-wise Self-attentive Hawkes Processes
Dongxia Wu, Tsuyoshi Idé, Aurélie Lozano, Georgios Kollias, Jiří Navrátil, Naoki Abe, Yi-An Ma, Rose Yu
Hawkes Process Granger Causality Instance Level Causal

August 23, 2022

Cardinality-Regularized Hawkes-Granger Model
Tsuyoshi Idé, Georgios Kollias, Dzung T. Phan, Naoki Abe
Hawkes Process Granger Causality Sparse Causal Instance Level Causal

February 25, 2022

Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization
Weijia Zhang, Xuanhui Zhang, Han-Wen Deng, Min-Ling Zhang
Distribution Generalization Instance Learning Multiple Instance Instance Prediction Instance Level Causal

Instance Level Causal

Papers

Causal Contextual Bandits with Adaptive Context

Learning Granger Causality from Instance-wise Self-attentive Hawkes Processes

Cardinality-Regularized Hawkes-Granger Model

Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization