ServiceNow AI Research

Causality

Causal Discovery with Language Models as Imperfect Experts
Causal Discovery with Language Models as Imperfect Experts
Understanding the causal relationships that underlie a system is a fundamental prerequisite to accurate decision-making. In this work, …
Workshop on Structured Probabilistic Inference & Generative Modeling (ICML),  2023.
PDF Cite Code Slides Video
Using Confounded Data in Offline RL
Using Confounded Data in Offline RL
In this work we consider the problem of confounding in offline RL, also referred to as the delusion problem. While it is known that …
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
PDF Cite Code Slides Video
Deconfounding Dynamic Treatment Regimes
Deconfounding Dynamic Treatment Regimes
Counterfactual prediction under sequences of actions is a fundamental problem in decision-making. Existing methods in causal inference …
SSC,  2022.
Cite
Typing assumptions improve identification in causal discovery - theory and algorithms
Typing assumptions improve identification in causal discovery - theory and algorithms
Causal discovery from observational data is a challenging task that can only be solved up to a set of equivalent solutions, called an …
Causal Learning and Reasoning (CLeaR),  2022.
PDF Cite Code
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the …
Conference on Neural Information Processing Systems (NeurIPS),  2021.
PDF Cite Code
Typing assumptions improve identification in causal discovery - Report and comments on future directions
Typing assumptions improve identification in causal discovery - Report and comments on future directions
Causal discovery from observational data is a challenging task that can only be solved up to a set of equivalent solutions, called an …
Workshop at the Neural Information Processing Systems (NeurIPS),  2021.
PDF Cite Code
Typing assumptions improve identification in causal discovery
Typing assumptions improve identification in causal discovery
Causal discovery from observational data is a challenging task that can only be solved up to a set of equivalent solutions, called an …
Workshop at the International Conference on Machine Learning (ICML),  2021.
PDF Cite Code
Variational Causal Networks: Approximate Bayesian Inference over Causal Structures
Variational Causal Networks: Approximate Bayesian Inference over Causal Structures
Learning the causal structure that underlies data is a crucial step towards robust real-world decision making. The majority of existing …
Workshop at the International Conference on Machine Learning (ICML),  2021.
PDF Cite Code
Differentiable Causal Discovery from Interventional Data
Differentiable Causal Discovery from Interventional Data
Learning a causal directed acyclic graph from data is a challenging task that involves solving a combinatorial problem for which the …
Conference on Neural Information Processing Systems (NeurIPS),  2020.
PDF Cite Code Video
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
We propose to meta-learn causal structures based on how fast a learner adapts to new distributions arising from sparse distributional …
International Conference on Learning Representations (ICLR),  2020.
PDF Cite Code Video