mlsanityData to 7 Oct 2026

PGODE: Towards High-quality System Dynamics Modeling

arXiv 2311.06554 ↗First posted 11 Nov 2023cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

This paper studies the problem of modeling multi-agent dynamical systems, where agents could interact mutually to influence their behaviors. Recent research predominantly uses geometric graphs to depict these mutual interactions, which are then captured by powerful graph neural networks (GNNs). However, predicting interacting dynamics in challenging scenarios such as out-of-distribution shift and complicated underlying rules remains unsolved. In this paper, we propose a new approach named Prototypical Graph ODE (PGODE) to address the problem. The core of PGODE is to incorporate prototype decomposition from contextual knowledge into a continuous graph ODE framework. Specifically, PGODE employs representation disentanglement and system parameters to extract both object-level and system-level contexts from historical trajectories, which allows us to explicitly model their independent influence and thus enhances the generalization capability under system changes. Then, we integrate these disentangled latent representations into a graph ODE model, which determines a combination of various interacting prototypes for enhanced model expressivity. The entire model is optimized using an end-to-end variational inference framework to maximize the likelihood. Extensive experiments in both in-distribution and out-of-distribution settings validate the superiority of PGODE compared to various baselines.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 73 of its 105 references that are in the map. First posted on arXiv 11 Nov 2023.

Builds on

73 of 105 references.

References · 73

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2018Neural Ordinary Differential Equationscited by 3,733
  7. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  8. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  9. 2019An Introduction to Variational Autoencoderscited by 997
  10. 2021E(n) Equivariant Graph Neural Networkscited by 951
  11. 2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 890
  12. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
38 more
  1. 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
  2. 2022Mixture-of-Experts with Expert Choice Routingcited by 611
  3. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  4. 2019Augmented Neural ODEscited by 396
  5. 2021COMBO: Conservative Offline Model-Based Policy Optimizationcited by 365
  6. 2018Neural Relational Inference for Interacting Systemscited by 339
  7. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 327
  8. 2020Inductive Biases for Deep Learning of Higher-Level Cognitioncited by 273
  9. 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
  10. 2023PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solverscited by 205
  11. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 184
  12. 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
  13. 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
  14. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  15. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  16. 2019Graph Neural Ordinary Differential Equationscited by 153
  17. 2019Continuous Graph Neural Networkscited by 114
  18. 2021Modeling Irregular Time Series with Continuous Recurrent Unitscited by 101
  19. 2023EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoningcited by 97
  20. 2021Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patternscited by 95
  21. 2022Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisitedcited by 87
  22. 2020SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimatescited by 75
  23. 2022Multivariate Time Series Forecasting with Dynamic Graph Neural ODEscited by 72
  24. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  25. 2023Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modelingcited by 63
  26. 2021Encoding physics to learn reaction-diffusion processescited by 61
  27. 2021MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Predictioncited by 61
  28. 2020Learning Continuous System Dynamics from Irregularly-Sampled Partial Observationscited by 60
  29. 2022An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditionscited by 54
  30. 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
  31. 2023From Zero to Turbulence: Generative Modeling for 3D Flow Simulationcited by 46
  32. 2022ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Datacited by 45
  33. 2021MALI: A memory efficient and reverse accurate integrator for Neural ODEscited by 42
  34. 2021Heavy Ball Neural Ordinary Differential Equationscited by 42
  35. 2022Learning Physical Dynamics with Subequivariant Graph Neural Networkscited by 38
  36. 2023Taming Local Effects in Graph-based Spatiotemporal Forecastingcited by 37
  37. 2020Evaluating Robustness to Input Perturbations for Neural Machine Translationcited by 36
  38. 2020"Hey, that's not an ODE": Faster ODE Adjoints via Seminormscited by 35

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 2.

7 papers.

  1. 2025Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networkscited by 14
  2. 2025STFlow: Data-Coupled Flow Matching for Geometric Trajectory Simulationcited by 7
  3. 2024System-Aware Neural ODE Processes for Few-Shot Bayesian Optimizationcited by 3
  4. 2024Graph Fourier Neural ODEs: Modeling Spatial-temporal Multi-scales in Molecular Dynamicscited by 2
  5. 2024Learning System Dynamics without Forgettingcited by 1
  6. 2026DGNet: Discrete Green Networks for Data-Efficient Learning of Spatiotemporal PDEscited by 1
  7. 2026Generalizing Dynamics Modeling More Easily from Representation Perspectivecited by 0