mlsanityData to 14 Oct 2026

Diffusion model for relational inference

arXiv 2401.16755 ↗First posted 30 Jan 2024cs.LG cs.AIcited by 2

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Dynamical behaviors of complex interacting systems, including brain activities, financial price movements, and physical collective phenomena, are associated with underlying interactions between the system's components. The issue of uncovering interaction relations in such systems using observable dynamics is called relational inference. In this study, we propose a Diffusion model for Relational Inference (DiffRI), inspired by a self-supervised method for probabilistic time series imputation. DiffRI learns to infer the probability of the presence of connections between components through conditional diffusion modeling.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 33 of its 63 references that are in the map. First posted on arXiv 30 Jan 2024.

Builds on

33 of 63 references.

Closest ancestors · 8

Same direction, newest first

  1. 2023Diffusion Models are Minimax Optimal Distribution Estimators3 Mar
  2. 2022Diffusion Models in Vision: A Survey10 Sep
  3. 2022Diffusion Models: A Comprehensive Survey of Methods and Applications2 Sep
  4. 2022Understanding Diffusion Models: A Unified Perspective25 Aug
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  7. 2020Denoising Diffusion Implicit Models6 Oct
  8. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  6. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  7. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  8. 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
  9. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 377
  10. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 337
  11. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 198
  12. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
13 more
  1. 2021Graph-Guided Network for Irregularly Sampled Multivariate Time Seriescited by 111
  2. 2020Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Datacited by 100
  3. 2022Diffusion models for missing value imputation in tabular datacited by 77
  4. 2021Explaining Time Series Predictions with Dynamic Maskscited by 73
  5. 2021Causal Inference for Time series Analysis: Problems, Methods and Evaluationcited by 42
  6. 2023CUTS: Neural Causal Discovery from Irregular Time-Series Datacited by 33
  7. 2022Sparse Graph Learning from Spatiotemporal Time Seriescited by 22
  8. 2023Probabilistic Imputation for Time-series Classification with Missing Datacited by 22
  9. 2018A General Deep Learning Framework for Network Reconstruction and Dynamics Learningcited by 16
  10. 2023Neural Relational Inference with Fast Modular Meta-learningcited by 16
  11. 2019Deep Neural Network Ensembles for Time Series Classificationcited by 13
  12. 2017Connectivity Inference from Neural Recording Data: Challenges, Mathematical Bases and Research Directionscited by 12
  13. 2021Neural Relational Inference with Efficient Message Passing Mechanismscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024Behavior-Inspired Neural Networks for Relational Inferencecited by 5
  2. 2026Structural Inference under Hidden Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models
  2. 2026From Uniform to Learned Graph Priors: Diffusion for Structure Discovery
  3. 2024Relational Diffusion Distillation for Efficient Image Generation
  4. 2025Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner
  5. 2022Relational Causal Models with Cycles:Representation and Reasoning
  6. 2025Capturing Conditional Dependence via Auto-regressive Diffusion Models
  7. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting
  8. 2026Analyzing and Improving Diffusion Models for Time-Series Data Imputation: A Proximal Recursion Perspective