# Neural Relational Inference with Efficient Message Passing Mechanisms

arXiv: https://arxiv.org/abs/2101.09486 · HTML: https://mlsanity.com/paper/2101.09486/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 23 Jan 2021.

## Builds on (most cited first, 18 of 18)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [GMAN: A Graph Multi-Attention Network for Traffic Prediction](https://mlsanity.com/paper/1911.08415/) (2019)
- [Neural Relational Inference for Interacting Systems](https://mlsanity.com/paper/1802.04687/) (2018)
- [Graph networks as learnable physics engines for inference and control](https://mlsanity.com/paper/1806.01242/) (2018)
- [Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions](https://mlsanity.com/paper/1802.10353/) (2018)
- [Visual Interaction Networks](https://mlsanity.com/paper/1706.01433/) (2017)
- [GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation](https://mlsanity.com/paper/1906.12192/) (2019)
- [VAIN: Attentional Multi-agent Predictive Modeling](https://mlsanity.com/paper/1706.06122/) (2017)
- [A General Deep Learning Framework for Network Reconstruction and Dynamics Learning](https://mlsanity.com/paper/1812.11482/) (2018)
- [Factorised Neural Relational Inference for Multi-Interaction Systems](https://mlsanity.com/paper/1905.08721/) (2019)
- [Data-driven Computational Social Science: A Survey](https://mlsanity.com/paper/2008.12372/) (2020)
- [Deep learning reveals hidden interactions in complex systems](https://mlsanity.com/paper/2001.02539/) (2020)

## Built on by (most cited first, 10 of 10)

- [Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction](https://mlsanity.com/paper/2305.14715/) (2023)
- [Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detection](https://mlsanity.com/paper/2412.19108/) (2024)
- [Causal Discovery from Conditionally Stationary Time Series](https://mlsanity.com/paper/2110.06257/) (2021)
- [Behavior-Inspired Neural Networks for Relational Inference](https://mlsanity.com/paper/2406.14746/) (2024)
- [Heterogeneous Interaction Modeling With Reduced Accumulated Error for Multi-Agent Trajectory Prediction](https://mlsanity.com/paper/2410.21342/) (2024)
- [Online Relational Inference for Evolving Multi-agent Interacting Systems](https://mlsanity.com/paper/2411.01442/) (2024)
- [Collective Relational Inference for learning heterogeneous interactions](https://mlsanity.com/paper/2305.00557/) (2023)
- [Diffusion model for relational inference](https://mlsanity.com/paper/2401.16755/) (2024)
- [From Uniform to Learned Graph Priors: Diffusion for Structure Discovery](https://mlsanity.com/paper/2606.11831/) (2026)
- [Structural Inference under Hidden Agents](https://mlsanity.com/paper/2609.18045/) (2026)

## Abstract (arXiv)

Many complex processes can be viewed as dynamical systems of interacting agents. In many cases, only the state sequences of individual agents are observed, while the interacting relations and the dynamical rules are unknown. The neural relational inference (NRI) model adopts graph neural networks that pass messages over a latent graph to jointly learn the relations and the dynamics based on the observed data. However, NRI infers the relations independently and suffers from error accumulation in multi-step prediction at dynamics learning procedure. Besides, relation reconstruction without prior knowledge becomes more difficult in more complex systems. This paper introduces efficient message passing mechanisms to the graph neural networks with structural prior knowledge to address these problems. A relation interaction mechanism is proposed to capture the coexistence of all relations, and a spatio-temporal message passing mechanism is proposed to use historical information to alleviate error accumulation. Additionally, the structural prior knowledge, symmetry as a special case, is introduced for better relation prediction in more complex systems. The experimental results on simulated physics systems show that the proposed method outperforms existing state-of-the-art methods.