mlsanityData to 7 Oct 2026

Learning Latent Structural Causal Models

arXiv 2210.13583 ↗First posted 24 Oct 2022cs.LG cs.AI stat.MEcited by 5

Not on the map. Why?

Abstract (arXiv)

Causal learning has long concerned itself with the accurate recovery of underlying causal mechanisms. Such causal modelling enables better explanations of out-of-distribution data. Prior works on causal learning assume that the high-level causal variables are given. However, in machine learning tasks, one often operates on low-level data like image pixels or high-dimensional vectors. In such settings, the entire Structural Causal Model (SCM) -- structure, parameters, textitand high-level causal variables -- is unobserved and needs to be learnt from low-level data. We treat this problem as Bayesian inference of the latent SCM, given low-level data. For linear Gaussian additive noise SCMs, we present a tractable approximate inference method which performs joint inference over the causal variables, structure and parameters of the latent SCM from random, known interventions. Experiments are performed on synthetic datasets and a causally generated image dataset to demonstrate the efficacy of our approach. We also perform image generation from unseen interventions, thereby verifying out of distribution generalization for the proposed causal model.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 58 of its 96 references that are in the map. First posted on arXiv 24 Oct 2022.

Builds on

58 of 96 references.

References · 58

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  3. 2016Variational Inference: A Review for Statisticianscited by 1,466
  4. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
  5. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  6. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  7. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 329
  8. 2016Ladder Variational Autoencoderscited by 315
  9. 2021GFlowNet Foundationscited by 286
  10. 2020AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradientscited by 282
  11. 2020Inductive Biases for Deep Learning of Higher-Level Cognitioncited by 273
  12. 2016Revisiting Classifier Two-Sample Testscited by 258
38 more
  1. 2019Gradient-Based Neural DAG Learningcited by 227
  2. 2021Contrastive Learning Inverts the Data Generating Processcited by 220
  3. 2020Differentiable Causal Discovery from Interventional Datacited by 218
  4. 2021Towards Causal Representation Learningcited by 207
  5. 2020DYNOTEARS: Structure Learning from Time-Series Datacited by 198
  6. 2020On the Role of Sparsity and DAG Constraints for Learning Linear DAGscited by 186
  7. 2013Learning Bayesian Networks: The Combination of Knowledge and Statistical Datacited by 185
  8. 2018Learning Latent Permutations with Gumbel-Sinkhorn Networkscited by 172
  9. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
  10. 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
  11. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  12. 2022Weakly supervised causal representation learningcited by 140
  13. 2022Interventional Causal Representation Learningcited by 140
  14. 2022CITRIS: Causal Identifiability from Temporal Intervened Sequencescited by 132
  15. 2019Learning Neural Causal Models from Unknown Interventionscited by 113
  16. 2021DiBS: Differentiable Bayesian Structure Learningcited by 105
  17. 2019Masked Gradient-Based Causal Structure Learningcited by 89
  18. 2016Discovering Causal Signals in Imagescited by 79
  19. 2021Desiderata for Representation Learning: A Causal Perspectivecited by 76
  20. 2021BCD Nets: Scalable Variational Approaches for Bayesian Causal Discoverycited by 68
  21. 2022Learning to Induce Causal Structurecited by 68
  22. 2020Weakly Supervised Disentangled Generative Causal Representation Learningcited by 67
  23. 2020DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networkscited by 66
  24. 2022Weakly Supervised Representation Learning with Sparse Perturbationscited by 64
  25. 2013Learning Gaussian Networkscited by 62
  26. 2021Learning latent causal graphs via mixture oraclescited by 55
  27. 2021DAGs with No Curl: An Efficient DAG Structure Learning Approachcited by 53
  28. 2021Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learningcited by 53
  29. 2019ABCD-Strategy: Budgeted Experimental Design for Targeted Causal Structure Discoverycited by 52
  30. 2017Learning linear structural equation models in polynomial time and sample complexitycited by 49
  31. 2022Interventions, Where and How? Experimental Design for Causal Models at Scalecited by 49
  32. 2022Differentiable DAG Samplingcited by 46
  33. 2021Variational Causal Networks: Approximate Bayesian Inference over Causal Structurescited by 43
  34. 2021Learning Neural Causal Models with Active Interventionscited by 40
  35. 2022Active Bayesian Causal Inferencecited by 34
  36. 2020Towards Scalable Bayesian Learning of Causal DAGscited by 33
  37. 2018Efficient Sampling and Structure Learning of Bayesian Networkscited by 28
  38. 2013The Bayesian Structural EM Algorithmcited by 26

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 2.

5 papers.

  1. 2022Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayescited by 30
  2. 2024LCA-on-the-Line: Benchmarking Out-of-Distribution Generalization with Class Taxonomiescited by 12
  3. 2023Neuro-Causal Factor Analysiscited by 4
  4. 2024Differentiable Causal Discovery For Latent Hierarchical Causal Modelscited by 3
  5. 2023Diffusion Based Causal Representation Learningcited by 0