mlsanityData to 7 Oct 2026

Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data

arXiv 2006.10833 ↗First posted 18 Jun 2020cs.LG stat.MLcited by 99

Not on the map. Why?

Abstract (arXiv)

On time-series data, most causal discovery methods fit a new model whenever they encounter samples from a new underlying causal graph. However, these samples often share relevant information which is lost when following this approach. Specifically, different samples may share the dynamics which describe the effects of their causal relations. We propose Amortized Causal Discovery, a novel framework that leverages such shared dynamics to learn to infer causal relations from time-series data. This enables us to train a single, amortized model that infers causal relations across samples with different underlying causal graphs, and thus leverages the shared dynamics information. We demonstrate experimentally that this approach, implemented as a variational model, leads to significant improvements in causal discovery performance, and show how it can be extended to perform well under added noise and hidden confounding.

Key facts. Cited by 99 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 14; 2023: 27; 2024: 19; 2025: 13; 2026: 13.

99 papers.

Sort:

By area:

  1. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 209
  2. 2023Causal Parrots: Large Language Models May Talk Causality But Are Not Causalcited by 146
  3. 2022Score matching enables causal discovery of nonlinear additive noise modelscited by 108
  4. 2022Amortized Inference for Causal Structure Learningcited by 89
  5. 2022Learning to Induce Causal Structurecited by 68
  6. 2022Temporally Disentangled Representation Learningcited by 59
  7. 2021Interpretable Models for Granger Causality Using Self-explaining Neural Networkscited by 44
  8. 2023Causal Discovery from Temporal Data: An Overview and New Perspectivescited by 43
  9. 2021Causal Inference for Time series Analysis: Problems, Methods and Evaluationcited by 42
  10. 2023Scalable Causal Discovery with Score Matchingcited by 42
  11. 2023CUTS+: High-dimensional Causal Discovery from Irregular Time-seriescited by 39
  12. 2023A Survey on Causal Discovery Methods for I.I.D. and Time Series Datacited by 35
38 more
  1. 2023CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discoverycited by 35
  2. 2023CUTS: Neural Causal Discovery from Irregular Time-Series Datacited by 32
  3. 2021EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use casecited by 30
  4. 2022Rhino: Deep Causal Temporal Relationship Learning With History-dependent Noisecited by 30
  5. 2021You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Predictioncited by 23
  6. 2023Temporally Disentangled Representation Learning under Unknown Nonstationaritycited by 21
  7. 2023Learning Manifold Dimensions with Conditional Variational Autoencoderscited by 20
  8. 2021Transferable Time-Series Forecasting under Causal Conditional Shiftcited by 18
  9. 2022Achieving Long-Term Fairness in Sequential Decision Makingcited by 18
  10. 2022A Review of Causality for Learning Algorithms in Medical Image Analysiscited by 18
  11. 2021Self-supervised Reinforcement Learning with Independently Controllable Subgoalscited by 16
  12. 2021Causal Multi-Agent Reinforcement Learning: Review and Open Problemscited by 16
  13. 2023Causal Reasoning: Charting a Revolutionary Course for Next-Generation AI-Native Wireless Networkscited by 16
  14. 2023Causal Semantic Communication for Digital Twins: A Generalizable Imitation Learning Approachcited by 14
  15. 2023Neural Structure Learning with Stochastic Differential Equationscited by 14
  16. 2022Learning Latent Causal Dynamicscited by 13
  17. 2021Causal Discovery from Conditionally Stationary Time Seriescited by 11
  18. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11
  19. 2025Learning Interactive World Model for Object-Centric Reinforcement Learningcited by 11
  20. 2023Discovering Mixtures of Structural Causal Models from Time Series Datacited by 10
  21. 2024Demystifying amortized causal discovery with transformerscited by 10
  22. 2024SPARTAN: A Sparse Transformer World Model Attending to What Matterscited by 10
  23. 2024Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Drivingcited by 9
  24. 2024Learning Granger Causality from Instance-wise Self-attentive Hawkes Processescited by 7
  25. 2021Learning interaction rules from multi-animal trajectories via augmented behavioral modelscited by 5
  26. 2024Large-Scale Targeted Cause Discovery via Learning from Simulated Datacited by 5
  27. 2024Behavior-Inspired Neural Networks for Relational Inferencecited by 4
  28. 2025Curious Causality-Seeking Agents Learn Meta Causal Worldcited by 4
  29. 2022Neural Information Squeezer for Causal Emergencecited by 3
  30. 2023Double Machine Learning Based Structure Identification from Temporal Datacited by 3
  31. 2024SPHINX: Structural Prediction using Hypergraph Inference Networkcited by 3
  32. 2024Online Relational Inference for Evolving Multi-agent Interacting Systemscited by 3
  33. 2025SDVDiag: A Modular Platform for the Diagnosis of Connected Vehicle Functionscited by 3
  34. 2026Disentangling Dynamical Systems: Causal Representation Learning Meets Local Sparse Attentioncited by 3
  35. 2021AI perspectives in Smart Cities and Communities to enable road vehicle automation and smart traffic controlcited by 2
  36. 2021Convolutions for Spatial Interaction Modelingcited by 2
  37. 2022DIDER: Discovering Interpretable Dynamically Evolving Relationscited by 2
  38. 2022Learning domain-specific causal discovery from time seriescited by 2

50 most cited of 99 All 99 (JSON)