mlsanityData to 14 Oct 2026

Neural Relational Inference for Interacting Systems

arXiv 1802.04687 ↗First posted 13 Feb 2018stat.ML cs.LGcited by 339

Not on the map. Why?

Abstract (arXiv)

Interacting systems are prevalent in nature, from dynamical systems in physics to complex societal dynamics. The interplay of components can give rise to complex behavior, which can often be explained using a simple model of the system's constituent parts. In this work, we introduce the neural relational inference (NRI) model: an unsupervised model that learns to infer interactions while simultaneously learning the dynamics purely from observational data. Our model takes the form of a variational auto-encoder, in which the latent code represents the underlying interaction graph and the reconstruction is based on graph neural networks. In experiments on simulated physical systems, we show that our NRI model can accurately recover ground-truth interactions in an unsupervised manner. We further demonstrate that we can find an interpretable structure and predict complex dynamics in real motion capture and sports tracking data.

Key facts. Cited by 339 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 1; 2021: 85; 2022: 81; 2023: 66; 2024: 53; 2025: 24; 2026: 28.

339 papers.

Sort:

By area:

  1. 2021E(n) Equivariant Graph Neural Networkscited by 965
  2. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 331
  3. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 270
  4. 2022GraphCast: Learning skillful medium-range global weather forecastingcited by 267
  5. 2021Geometric and Physical Quantities Improve E(3) Equivariant Message Passingcited by 228
  6. 2021Towards Causal Representation Learningcited by 209
  7. 2021PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learningcited by 182
  8. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 174
  9. 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 171
  10. 2022GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoningcited by 128
  11. 2022Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecastingcited by 117
  12. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 113
38 more
  1. 2022Equivariance with Learned Canonicalization Functionscited by 109
  2. 2022Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvaturecited by 98
  3. 2023EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoningcited by 97
  4. 2021Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networkscited by 95
  5. 2022Remember Intentions: Retrospective-Memory-based Trajectory Predictioncited by 86
  6. 2022Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 85
  7. 2023Everything is Connected: Graph Neural Networkscited by 85
  8. 2021Beltrami Flow and Neural Diffusion on Graphscited by 84
  9. 2021Neural Production Systems: Learning Rule-Governed Visual Dynamicscited by 75
  10. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  11. 2021Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modelingcited by 69
  12. 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
  13. 2022Equivariant Graph Mechanics Networks with Constraintscited by 68
  14. 2022When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learningcited by 65
  15. 2022ComPhy: Compositional Physical Reasoning of Objects and Events from Videoscited by 63
  16. 2022TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphscited by 59
  17. 2021ForceNet: A Graph Neural Network for Large-Scale Quantum Calculationscited by 58
  18. 2022Geometrically Equivariant Graph Neural Networks: A Surveycited by 56
  19. 2021Learning latent causal graphs via mixture oraclescited by 55
  20. 2023Clifford Group Equivariant Neural Networkscited by 55
  21. 2023Leveraging Future Relationship Reasoning for Vehicle Trajectory Predictioncited by 48
  22. 2022Message passing all the way upcited by 47
  23. 2021Interpretable Models for Granger Causality Using Self-explaining Neural Networkscited by 45
  24. 2022MoCoDA: Model-based Counterfactual Data Augmentationcited by 44
  25. 2021Spatial Dual-Modality Graph Reasoning for Key Information Extractioncited by 43
  26. 2022Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecastingcited by 42
  27. 2022Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Seriescited by 42
  28. 2021Relating Graph Neural Networks to Structural Causal Modelscited by 41
  29. 2023Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Spacecited by 41
  30. 2021Automated Machine Learning on Graphs: A Surveycited by 39
  31. 2022Learning Physical Dynamics with Subequivariant Graph Neural Networkscited by 39
  32. 2024Equivariant Graph Neural Operator for Modeling 3D Dynamicscited by 38
  33. 2021Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Predictioncited by 37
  34. 2021RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecastingcited by 36
  35. 2022Is a Modular Architecture Enough?cited by 36
  36. 2021Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Trackingcited by 35
  37. 2021Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphscited by 35
  38. 2022Multi-modal Graph Learning for Disease Predictioncited by 34

50 most cited of 339 All 339 (JSON)