---
OA_place: publisher
OA_type: gold
_id: '19005'
abstract:
- lang: eng
  text: "Causal representation learning promises to extend causal models to hidden
    causal\r\nvariables from raw entangled measurements. However, most progress has
    focused\r\non proving identifiability results in different settings, and we are
    not aware of any\r\nsuccessful real-world application. At the same time, the field
    of dynamical systems\r\nbenefited from deep learning and scaled to countless applications
    but does not allow\r\nparameter identification. In this paper, we draw a clear
    connection between the two\r\nand their key assumptions, allowing us to apply
    identifiable methods developed\r\nin causal representation learning to dynamical
    systems. At the same time, we can\r\nleverage scalable differentiable solvers
    developed for differential equations to build\r\nmodels that are both identifiable
    and practical. Overall, we learn explicitly controllable models that isolate the
    trajectory-specific parameters for further downstream\r\ntasks such as out-of-distribution
    classification or treatment effect estimation. We\r\nexperiment with a wind simulator
    with partially known factors of variation. We\r\nalso apply the resulting model
    to real-world climate data and successfully answer\r\ndownstream causal questions
    in line with existing literature on climate change.\r\nCode is available at https://github.com/CausalLearningAI/crl-dynamical-systems."
acknowledgement: "We thank Niklas Boers for recommending the SpeedyWeather simulator
  and Valentino Maiorca\r\nfor guidance on Fourier transformation for SST data. We
  are also grateful to Shimeng Huang and Riccardo Cadei for their feedback on the
  treatment effect estimation experiment and to Jiale Chen and Adeel Pervez for their
  assistance with the solver implementation. Finally, we appreciate the anonymous
  reviewers for their insightful suggestions, which helped improve the manuscript. "
alternative_title:
- Advances in Neural Information Processing Systems
article_processing_charge: No
arxiv: 1
author:
- first_name: Dingling
  full_name: Yao, Dingling
  id: d3e02e50-48a8-11ee-8f62-c108061797fa
  last_name: Yao
- first_name: Caroline J
  full_name: Muller, Caroline J
  id: f978ccb0-3f7f-11eb-b193-b0e2bd13182b
  last_name: Muller
  orcid: 0000-0001-5836-5350
- first_name: Francesco
  full_name: Locatello, Francesco
  id: 26cfd52f-2483-11ee-8040-88983bcc06d4
  last_name: Locatello
  orcid: 0000-0002-4850-0683
citation:
  ama: 'Yao D, Muller CJ, Locatello F. Marrying causal representation learning with
    dynamical systems for science. In: <i>38th Conference on Neural Information Processing
    Systems</i>. Vol 37. Neural Information Processing Systems Foundation; 2024.'
  apa: 'Yao, D., Muller, C. J., &#38; Locatello, F. (2024). Marrying causal representation
    learning with dynamical systems for science. In <i>38th Conference on Neural Information
    Processing Systems</i> (Vol. 37). Vancouver, Canada: Neural Information Processing
    Systems Foundation.'
  chicago: Yao, Dingling, Caroline J Muller, and Francesco Locatello. “Marrying Causal
    Representation Learning with Dynamical Systems for Science.” In <i>38th Conference
    on Neural Information Processing Systems</i>, Vol. 37. Neural Information Processing
    Systems Foundation, 2024.
  ieee: D. Yao, C. J. Muller, and F. Locatello, “Marrying causal representation learning
    with dynamical systems for science,” in <i>38th Conference on Neural Information
    Processing Systems</i>, Vancouver, Canada, 2024, vol. 37.
  ista: 'Yao D, Muller CJ, Locatello F. 2024. Marrying causal representation learning
    with dynamical systems for science. 38th Conference on Neural Information Processing
    Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information
    Processing Systems, vol. 37.'
  mla: Yao, Dingling, et al. “Marrying Causal Representation Learning with Dynamical
    Systems for Science.” <i>38th Conference on Neural Information Processing Systems</i>,
    vol. 37, Neural Information Processing Systems Foundation, 2024.
  short: D. Yao, C.J. Muller, F. Locatello, in:, 38th Conference on Neural Information
    Processing Systems, Neural Information Processing Systems Foundation, 2024.
conference:
  end_date: 2024-12-16
  location: Vancouver, Canada
  name: 'NeurIPS: Neural Information Processing Systems'
  start_date: 2024-12-16
corr_author: '1'
date_created: 2025-02-05T07:49:00Z
date_published: 2024-12-01T00:00:00Z
date_updated: 2025-07-10T11:51:32Z
day: '01'
ddc:
- '000'
- '550'
department:
- _id: CaMu
- _id: FrLo
external_id:
  arxiv:
  - '2405.13888'
file:
- access_level: open_access
  checksum: fe8832367e7143876f178244385d859e
  content_type: application/pdf
  creator: dernst
  date_created: 2025-02-05T07:44:58Z
  date_updated: 2025-02-05T07:44:58Z
  file_id: '19006'
  file_name: 2024_NeurIPS_Yao.pdf
  file_size: 2595855
  relation: main_file
  success: 1
file_date_updated: 2025-02-05T07:44:58Z
has_accepted_license: '1'
intvolume: '        37'
language:
- iso: eng
license: https://creativecommons.org/licenses/by/4.0/
month: '12'
oa: 1
oa_version: Published Version
publication: 38th Conference on Neural Information Processing Systems
publication_status: published
publisher: Neural Information Processing Systems Foundation
quality_controlled: '1'
related_material:
  link:
  - relation: software
    url: https://github.com/CausalLearningAI/crl-dynamical-systems
scopus_import: '1'
status: public
title: Marrying causal representation learning with dynamical systems for science
tmp:
  image: /images/cc_by.png
  legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
  name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
  short: CC BY (4.0)
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 37
year: '2024'
...