mlsanityData to 14 Oct 2026

Diffusion-Based Representation Learning

arXiv 2105.14257 ↗First posted 29 May 2021cs.LG cs.CVcited by 57

Not on the map. Why?

Cited by 44 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Diffusion-based methods represented as stochastic differential equations on a continuous-time domain have recently proven successful as a non-adversarial generative model. Training such models relies on denoising score matching, which can be seen as multi-scale denoising autoencoders. Here, we augment the denoising score matching framework to enable representation learning without any supervised signal. GANs and VAEs learn representations by directly transforming latent codes to data samples. In contrast, the introduced diffusion-based representation learning relies on a new formulation of the denoising score matching objective and thus encodes the information needed for denoising. We illustrate how this difference allows for manual control of the level of details encoded in the representation. Using the same approach, we propose to learn an infinite-dimensional latent code that achieves improvements of state-of-the-art models on semi-supervised image classification. We also compare the quality of learned representations of diffusion score matching with other methods like autoencoder and contrastively trained systems through their performances on downstream tasks.

Key facts. Cited by 57 papers in the map (data through 14 Oct 2026). Builds on 37 of its 66 references that are in the map. First posted on arXiv 29 May 2021.

Builds on

37 of 66 references.

References · 37

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  9. 2017Neural Discrete Representation Learningcited by 4,712
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  11. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  12. 2020Exploring Simple Siamese Representation Learningcited by 2,866
25 more
  1. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  2. 2016Matching Networks for One Shot Learningcited by 2,255
  3. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  4. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  5. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  6. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,043
  7. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  8. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  9. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
  10. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  11. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
  12. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speedcited by 348
  13. 2015A note on the evaluation of generative modelscited by 292
  14. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 270
  15. 2020Learning Gradient Fields for Shape Generationcited by 245
  16. 2019Large Scale Adversarial Representation Learningcited by 239
  17. 2021Symbolic Music Generation with Diffusion Modelscited by 154
  18. 2016Controlling Perceptual Factors in Neural Style Transfercited by 100
  19. 2020Adversarial score matching and improved sampling for image generationcited by 96
  20. 2018MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasetscited by 49
  21. 2018Deep Energy Estimator Networkscited by 34
  22. 2018On Catastrophic Forgetting and Mode Collapse in Generative Adversarial Networkscited by 17
  23. 2014Scheduled denoising autoencoderscited by 11
  24. 2018Tempered Adversarial Networkscited by 6
  25. 2017Annealed Generative Adversarial Networkscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 13; 2024: 16; 2025: 15; 2026: 8.

57 papers.

Sort:

By area:

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  2. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 703
  3. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Surveycited by 273
  4. 2022Diffusion Models for Video Prediction and Infillingcited by 135
  5. 2023Denoising Diffusion Autoencoders are Unified Self-supervised Learnerscited by 130
  6. 2023Diffusion Model as Representation Learnercited by 95
  7. 2025What matters for Representation Alignment: Global Information or Spatial Structure?cited by 84
  8. 2023SODA: Bottleneck Diffusion Models for Representation Learningcited by 77
  9. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 60
  10. 2024Diffusion Models and Representation Learning: A Surveycited by 54
  11. 2024On the Challenges and Opportunities in Generative AIcited by 31
  12. 2023Learning Data Representations with Joint Diffusion Modelscited by 22
38 more
  1. 2023From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modelingcited by 22
  2. 2024UniGEM: A Unified Approach to Generation and Property Prediction for Moleculescited by 21
  3. 2024Causal Diffusion Autoencoders: Toward Counterfactual Generation via Diffusion Probabilistic Modelscited by 18
  4. 2025Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modelingcited by 18
  5. 2023DiffEnc: Variational Diffusion with a Learned Encodercited by 17
  6. 2024Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstractioncited by 17
  7. 2024Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentationcited by 16
  8. 2023Internally Rewarded Reinforcement Learningcited by 14
  9. 2023Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Predictioncited by 13
  10. 2023Directional diffusion models for graph representation learningcited by 13
  11. 2024Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Modelscited by 12
  12. 2022From Points to Functions: Infinite-dimensional Representations in Diffusion Modelscited by 11
  13. 2023Emerging Synergies in Causality and Deep Generative Models: A Surveycited by 10
  14. 2025Diffusion Counterfactual Generation with Semantic Abductioncited by 10
  15. 2023Exploring Compositional Visual Generation with Latent Classifier Guidancecited by 9
  16. 20254D Visual Pre-training for Robot Learningcited by 8
  17. 2022Representation Learning with Diffusion Modelscited by 6
  18. 2025Inversion-DPO: Precise and Efficient Post-Training for Diffusion Modelscited by 6
  19. 2024An Analysis of Human Alignment of Latent Diffusion Modelscited by 5
  20. 2025DiffNMR: Diffusion Models for Nuclear Magnetic Resonance Spectra Elucidationcited by 5
  21. 2026DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformerscited by 5
  22. 2025Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical Imagingcited by 4
  23. 2024Explaining latent representations of generative models with large multimodal modelscited by 3
  24. 2024Feature-guided score diffusion for sampling conditional densitiescited by 3
  25. 2024Unified Auto-Encoding with Masked Diffusioncited by 2
  26. 2024Assessing Open-world Forgetting in Generative Image Model Customizationcited by 2
  27. 2024Pretrained Reversible Generation as Unsupervised Visual Representation Learningcited by 2
  28. 2024Nested Diffusion Models Using Hierarchical Latent Priorscited by 2
  29. 2025Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptationcited by 2
  30. 2024DINTR: Tracking via Diffusion-based Interpolationcited by 1
  31. 2025Graffe: Graph Representation Learning via Diffusion Probabilistic Modelscited by 1
  32. 2025Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Reviewcited by 1
  33. 2025EEGDM: Learning EEG Representation with Latent Diffusion Modelcited by 1
  34. 2026Evaluating the Representation Space of Diffusion Models via Self-Supervised Principlescited by 1
  35. 2026Probing Diffusion Denoising Dynamics for Contrastive Representation Learningcited by 1
  36. 2026DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformerscited by 1
  37. 2023Diffusion Based Causal Representation Learningcited by 0
  38. 2025Discriminative protein sequence modelling with Latent Space Diffusioncited by 0

50 most cited of 57 All 57 (JSON)