ServiceNow AI Research

Causality

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
Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning
Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning
Language model activations entangle concepts that mediate their behavior, making it difficult to interpret these factors, which has …
Navita Goyal, Hal Daumé III, Alexandre Drouin, Dhanya Sridhar
Neural Information Processing Systems (NeurIPS),  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, Dhanya Sridhar, Alexandre Drouin
Causal Learning and Reasoning (CLeaR),  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
Multi-View Causal Representation Learning with Partial Observability
Multi-View Causal Representation Learning with Partial Observability
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as …
Dingling Yao, Danru Xu, Perouz Taslakian, Sébastien Lachapelle, Sara Magliacane, Julius von Kügelgen, Francesco Locatello
International Conference of Learning Representations (ICLR),  2024.
Paper Cite Code
Towards Disentangled High-level Causal Explanations in Text
In this work, we propose a causal representation learning framework for learning disentangled and intervenable high-level explanations …
Navita Goyal, Hal Daumé III, Alexandre Drouin, Dhanya Sridhar
Mid-Atlantic Student Colloquium on Speech, Language and Learning,  2024.
Cite
A Sparsity Principle for Partially Observable Causal
A Sparsity Principle for Partially Observable Causal
Causal representation learning (CRL) aims at identifying high-level causal variables from low-level data, e.g. images. Current methods …
Danru Xu, Dingling Yao, Perouz Taslakian, Sébastien Lachapelle, Julius von Kügelgen, Francesco Locatello, Sara Magliacane
Workshop at the Neural Information Processing Systems (NeurIPS),  2023.
Paper Cite
Multi-View Causal Representation Learning with Partial Observability
Multi-View Causal Representation Learning with Partial Observability
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as …
Dingling Yao, Danru Xu, Perouz Taslakian, Sébastien Lachapelle, Sara Magliacane, Julius von Kügelgen, Francesco Locatello
Workshop at the Neural Information Processing Systems (NeurIPS),  2023.
Paper Cite
Using Confounded Data in Latent Model-Based Reinforcement Learning
Using Confounded Data in Latent Model-Based Reinforcement Learning
In the presence of confounding, naively using off-the-shelf offline reinforcement learning (RL) algorithms leads to sub-optimal …
Maxime Gasse, Damien Grasset, Pierre-Yves Oudeyer, Guillaume Gaudron
Transactions on Machine Learning Research (TMLR),  2023.
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