ServiceNow AI Research

Causal Discovery

Can large language models build causal graphs?
Can large language models build causal graphs? 
Building causal graphs can be a laborious process. To ensure all relevant causal pathways have been captured, researchers often have to …
Tibor Schuster, Stephanie Long, Alexandre Piche
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
Paper Cite Code
Learning Discrete Directed Acyclic Graphs via Backpropagation
Learning Discrete Directed Acyclic Graphs via Backpropagation
Recently continuous relaxations have been proposed in order to learn directed acyclic graphs (DAGs) by backpropagation, instead of …
Andrew J. Wren, Pasquale Minervini, Luca Franceschi, Valentina Zantedeschi
Workshop at the Neural Information Processing Systems (NeurIPS),  2022.
Paper 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 …
Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste, Sébastien Lachapelle, Alexandre Drouin
Causal Learning and Reasoning (CLeaR),  2022.
Paper 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 …
Nan Rosemary Ke, Aniket Didolkar, Sarthak Mittal, Anirudh Goyal, Guillaume Lajoie, Danilo Rezende, Yoshua Bengio, Christopher Pal, Stefan Bauer , Michael C. Mozer
Conference on Neural Information Processing Systems (NeurIPS),  2021.
Paper 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 …
Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste, Sébastien Lachapelle, Alexandre Drouin
Workshop at the Neural Information Processing Systems (NeurIPS),  2021.
Paper 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 …
Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste, Sébastien Lachapelle, Alexandre Drouin
Workshop at the International Conference on Machine Learning (ICML),  2021.
Paper 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 …
Philippe Brouillard, Sébastien Lachapelle, Alexandre Lacoste, Simon Lcoste-Julien, Alexandre Drouin
Conference on Neural Information Processing Systems (NeurIPS),  2020.
Paper Cite Code Video
Gradient-Based Neural DAG Learning with Interventions
Gradient-Based Neural DAG Learning with Interventions
Decision making based on statistical association alone can be a dangerous en- deavor due to non-causal associations. Ideally, one would …
Philippe Brouillard, Alexandre Drouin, Sébastien Lachapelle, Alexandre Lacoste, Simon Lcoste-Julien
Workshop at the International Conference on Learning Representations (ICLR),  2020.
Paper Cite Code Video