mlsanityData to 7 Oct 2026

Composing graphical models with neural networks for structured representations and fast inference

arXiv 1603.06277 ↗First posted 20 Mar 2016stat.MLcited by 113

Not on the map. Why?

Abstract (arXiv)

We propose a general modeling and inference framework that composes probabilistic graphical models with deep learning methods and combines their respective strengths. Our model family augments graphical structure in latent variables with neural network observation models. For inference, we extend variational autoencoders to use graphical model approximating distributions with recognition networks that output conjugate potentials. All components of these models are learned simultaneously with a single objective, giving a scalable algorithm that leverages stochastic variational inference, natural gradients, graphical model message passing, and the reparameterization trick. We illustrate this framework with several example models and an application to mouse behavioral phenotyping.

Key facts. Cited by 113 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 0; 2021: 29; 2022: 20; 2023: 22; 2024: 16; 2025: 15; 2026: 9.

113 papers.

Sort:

By area:

  1. 2022Identifiability of deep generative models without auxiliary informationcited by 70
  2. 2021Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICAcited by 64
  3. 2023Posterior Collapse and Latent Variable Non-identifiabilitycited by 57
  4. 2024SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizercited by 55
  5. 2023Learning nonparametric latent causal graphs with unknown interventionscited by 34
  6. 2021Multi-Facet Clustering Variational Autoencoderscited by 28
  7. 2021A Deep Variational Approach to Clustering Survival Datacited by 25
  8. 2022Learning Options via Compressioncited by 22
  9. 2023Generative learning for nonlinear dynamicscited by 22
  10. 2021Deep Bayesian Unsupervised Lifelong Learningcited by 21
  11. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  12. 2021Amortized Variational Inference for Simple Hierarchical Modelscited by 19
38 more
  1. 2021Deep Explicit Duration Switching Models for Time Seriescited by 17
  2. 2022Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Modelscited by 16
  3. 2025LLM/Agent-as-Data-Analyst: A Surveycited by 15
  4. 2021Cauchy-Schwarz Regularized Autoencodercited by 13
  5. 2022Concept Graph Neural Networks for Surgical Video Understandingcited by 13
  6. 2022ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Imagescited by 12
  7. 2023Generative Causal Representation Learning for Out-of-Distribution Motion Forecastingcited by 12
  8. 2021On Incorporating Inductive Biases into VAEscited by 11
  9. 2022Neural Graphical Modelscited by 11
  10. 2023Revisiting Structured Variational Autoencoderscited by 11
  11. 2024Variational Inference for Uncertainty Quantification: an Analysis of Trade-offscited by 11
  12. 2021Variational Inference for Continuous-Time Switching Dynamical Systemscited by 9
  13. 2023On the Identifiability of Switching Dynamical Systemscited by 9
  14. 2021Breiman's two cultures: You don't have to choose sidescited by 8
  15. 2021Unsupervised Learning of Neurosymbolic Encoderscited by 8
  16. 2021Toward a `Standard Model' of Machine Learningcited by 8
  17. 2018CompILE: Compositional Imitation Learning and Executioncited by 7
  18. 2021Lossless compression with state space models using bits back codingcited by 6
  19. 2021Learning interaction rules from multi-animal trajectories via augmented behavioral modelscited by 5
  20. 2021Introspective Robot Perception using Smoothed Predictions from Bayesian Neural Networkscited by 5
  21. 2022Time Series Clustering with an EM algorithm for Mixtures of Linear Gaussian State Space Modelscited by 5
  22. 2022Unsupervised representation learning with recognition-parametrised probabilistic modelscited by 5
  23. 2024Dimension-independent rates for structured neural density estimationcited by 5
  24. 2021Lossless Compression with Latent Variable Modelscited by 4
  25. 2021Online Unsupervised Learning of Visual Representations and Categoriescited by 4
  26. 2022Learning Sequential Latent Variable Models from Multimodal Time Series Datacited by 4
  27. 2023Neuro-Causal Factor Analysiscited by 4
  28. 2023Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectivescited by 4
  29. 2023Identifiable Feature Learning for Spatial Data with Nonlinear ICAcited by 4
  30. 2024Provably Scalable Black-Box Variational Inference with Structured Variational Familiescited by 4
  31. 2024Gradient-free variational learning with conditional mixture networkscited by 4
  32. 2025Conformal Prediction for Time-series Forecasting with Change Pointscited by 4
  33. 2025A Unifying Framework for Parallelizing Sequential Models with Linear Dynamical Systemscited by 4
  34. 2021Segmenting Hybrid Trajectories using Latent ODEscited by 3
  35. 2021Self-Supervised Inference in State-Space Modelscited by 3
  36. 2022Markov Chain Monte Carlo for Continuous-Time Switching Dynamical Systemscited by 3
  37. 2023A Causal Ordering Prior for Unsupervised Representation Learningcited by 3
  38. 2023Variational Temporal IRT: Fast, Accurate, and Explainable Inference of Dynamic Learner Proficiencycited by 3

50 most cited of 113 All 113 (JSON)