ServiceNow AI Research

Causal Discovery

Causal Discovery With Metadata-Informed Latent Types
Causal Discovery With Metadata-Informed Latent Types
Causal discovery seeks to recover causal structure from data but the underlying graph is typically identifiable only up to its Markov …
Philippe Brouillard, Dhanya Sridhar, Alexandre Drouin
Conference on Uncertainty in Artificial Intelligence (UAI),  2026.
Cite
Learning a Spatial Partitioning and its Causal Relations from Temporal Data
Learning a Spatial Partitioning and its Causal Relations from Temporal Data
Scientific research often seeks to understand the causal structure underlying high-level variables in a system. For example, climate …
Philippe Brouillard, Sébastien Lachapelle, Julia Kaltenborn, Yaniv Gurwicz, Dhanya Sridhar, Alexandre Drouin, Peer Nowack, Jakob Runge, David Rolnick
Causal Learning and Reasoning (CLeaR),  2026.
Paper Cite Code
The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications
The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications
Causal discovery aims to automatically uncover causal relationships from data, a capability with significant potential across many …
Philippe Brouillard, Chandler Squires, Jonas Wahl, Konrad P. Kording, Karen Sachs, Dhanya Sridhar, Alexandre Drouin
Causal Learning and Reasoning (CLeaR),  2025.
Paper Cite Code
Learning to Defer for Causal Discovery with Imperfect Experts
Learning to Defer for Causal Discovery with Imperfect Experts
Integrating expert knowledge, e.g. from large language models, into causal discovery algorithms can be challenging when the knowledge …
Oscar Clivio, Divyat Mahajan, Perouz Taslakian, Sara Magliacane, Ioannis Mitliagkas, Valentina Zantedeschi, Alexandre Drouin
Workshop at the International Conference of Learning Representation (ICLR),  2025.
Paper Cite
The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications
The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications
Causal discovery aims to automatically uncover causal relationships from data, a capability with significant potential across many …
Philippe Brouillard, Chandler Squires, Jonas Wahl, Konrad P. Kording, Karen Sachs, Alexandre Drouin, Dhanya Sridhar
Workshop at the International Conference of Learning Representation (ICLR),  2025.
Paper Cite Code
A Sparsity Principle for Partially Observable Causal Representation Learning
A Sparsity Principle for Partially Observable Causal Representation Learning
Causal representation learning aims at identifying high-level causal variables from perceptual data. Most methods assume that all …
Danru Xu, Dingling Yao, Sébastien Lachapelle, Perouz Taslakian, Sara Magliacane, Francesco Locatello, Julius von Kügelgen
International Conference on Machine Learning (ICML),  2024.
Paper Cite Code
Invariant Causal Set Covering Machines
Invariant Causal Set Covering Machines
Rule-based models, such as decision trees, appeal to practitioners due to their interpretable nature. However, the learning algorithms …
Thibaud Godon, Baptiste Bauvin, Pascal Germain, Jacques Corbeil, Alexandre Drouin
Workshop on Spurious Correlations, Invariance, and Stability (ICML),  2023.
Paper Cite Code
Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation
Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation
The practical utility of causality in decision-making is widely recognized, with causal discovery and inference being inherently …
Chris Chinenye Emezue, Alexandre Drouin, Tristan Deleu, Stefan Bauer , Yoshua Bengio
Workshop on Structured Probabilistic Inference & Generative Modeling (ICML),  2023.
Paper Cite
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, …
Stephanie Long, Alexandre Piche, Valentina Zantedeschi, Tibor Schuster, Alexandre Drouin
Workshop on Structured Probabilistic Inference & Generative Modeling (ICML),  2023.
Paper Cite Code Slides Video
DAG Learning on the Permutahedron
DAG Learning on the Permutahedron

We propose a continuous optimization framework for discovering a latent directed acyclic graph (DAG) from observational data. Our …

Valentina Zantedeschi, Luca Franceschi, Jean Kaddour, Matt Kusner, Vlad Niculae
International Conference of Learning Representations (ICLR),  2023.
Paper Cite Code Slides