mlsanityData to 7 Oct 2026

Diffusion Based Causal Representation Learning

arXiv 2311.05421 ↗First posted 9 Nov 2023cs.LG stat.MEcited by 0

On the map: LLM reasoning → Causal reasoning in LLMs

Abstract (arXiv)

Causal reasoning can be considered a cornerstone of intelligent systems. Having access to an underlying causal graph comes with the promise of cause-effect estimation and the identification of efficient and safe interventions. However, learning causal representations remains a major challenge, due to the complexity of many real-world systems. Previous works on causal representation learning have mostly focused on Variational Auto-Encoders (VAE). These methods only provide representations from a point estimate, and they are unsuitable to handle high dimensions. To overcome these problems, we proposed a new Diffusion-based Causal Representation Learning (DCRL) algorithm. This algorithm uses diffusion-based representations for causal discovery. DCRL offers access to infinite dimensional latent codes, which encode different levels of information in the latent code. In a first proof of principle, we investigate the use of DCRL for causal representation learning. We further demonstrate experimentally that this approach performs comparably well in identifying the causal structure and causal variables.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning. Builds on 41 of its 57 references that are in the map. First posted on arXiv 9 Nov 2023.

Builds on

41 of 57 references.

References · 41

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2022Video Diffusion Modelscited by 2,280
  10. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  11. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  12. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
29 more
  1. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  2. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speedcited by 344
  3. 2022Understanding Diffusion Models: A Unified Perspectivecited by 337
  4. 2022Diffusion Models already have a Semantic Latent Spacecited by 324
  5. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  6. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 263
  7. 2020Learning Gradient Fields for Shape Generationcited by 245
  8. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  9. 2021Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAcited by 158
  10. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  11. 2022SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Modelscited by 146
  12. 2022Weakly supervised causal representation learningcited by 140
  13. 2022Diffusion Models for Video Prediction and Infillingcited by 134
  14. 2019Are Disentangled Representations Helpful for Abstract Visual Reasoning?cited by 100
  15. 2019Weakly Supervised Disentanglement with Guaranteescited by 82
  16. 2021Efficient Neural Causal Discovery without Acyclicity Constraintscited by 82
  17. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  18. 2022Weakly Supervised Representation Learning with Sparse Perturbationscited by 64
  19. 2021Diffusion-Based Representation Learningcited by 57
  20. 2023An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learningcited by 49
  21. 2023InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Modelscited by 48
  22. 2020CausalVAE: Structured Causal Disentanglement in Variational Autoencodercited by 47
  23. 2018Deep Energy Estimator Networkscited by 34
  24. 2022Identifying Weight-Variant Latent Causal Modelscited by 33
  25. 2022Inductive Biases for Object-Centric Representations in the Presence of Complex Texturescited by 13
  26. 2018Tempered Adversarial Networkscited by 6
  27. 2022Representation Learning with Diffusion Modelscited by 6
  28. 2022Learning Latent Structural Causal Modelscited by 5
  29. 2017Annealed Generative Adversarial Networkscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Causal Diffusion Autoencoders: Toward Counterfactual Generation via Diffusion Probabilistic Models
  2. 2023Modeling Causal Mechanisms with Diffusion Models for Interventional and Counterfactual Queries
  3. 2025Causal-Symbolic Meta-Learning (CSML): Inducing Causal World Models for Few-Shot Generalization
  4. 2025The Third Pillar of Causal Analysis? A Measurement Perspective on Causal Representations
  5. 2023Diffusion Model in Causal Inference with Unmeasured Confounders
  6. 2026CausalGDP: Causality-Guided Diffusion Policies for Reinforcement Learning
  7. 2026Smoothing the Landscape: Causal Structure Learning via Diffusion Denoising Objectives
  8. 2026CausalSteward: An Agentic Divide-Conquer-Combine Copilot for Causal Discovery