# A General Deep Learning Framework for Network Reconstruction and Dynamics Learning

arXiv: https://arxiv.org/abs/1812.11482 · HTML: https://mlsanity.com/paper/1812.11482/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2018.

## Built on by (most cited first, 16 of 16)

- [A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning](https://mlsanity.com/paper/2110.01515/) (2021)
- [Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems](https://mlsanity.com/paper/2306.13867/) (2023)
- [Neural Relational Inference with Efficient Message Passing Mechanisms](https://mlsanity.com/paper/2101.09486/) (2021)
- [Similarity-Based Equational Inference in Physics](https://mlsanity.com/paper/2103.13496/) (2021)
- [Learning Heterogeneous Interaction Strengths by Trajectory Prediction with Graph Neural Network](https://mlsanity.com/paper/2208.13179/) (2022)
- [Neural Network Pruning by Gradient Descent](https://mlsanity.com/paper/2311.12526/) (2023)
- [Neural Information Squeezer for Causal Emergence](https://mlsanity.com/paper/2201.10154/) (2022)
- [Structural Inference of Networked Dynamical Systems with Universal Differential Equations](https://mlsanity.com/paper/2207.04962/) (2022)
- [Learning Continuous Network Emerging Dynamics from Scarce Observations via Data-Adaptive Stochastic Processes](https://mlsanity.com/paper/2310.16466/) (2023)
- [Diffusion model for relational inference](https://mlsanity.com/paper/2401.16755/) (2024)
- [Dynamic Relation Discovery and Utilization in Multi-Entity Time Series Forecasting](https://mlsanity.com/paper/2202.10586/) (2022)
- [GINA: Neural Relational Inference From Independent Snapshots](https://mlsanity.com/paper/2105.14329/) (2021)
- [Deep Demixing: Reconstructing the Evolution of Network Epidemics](https://mlsanity.com/paper/2306.07938/) (2023)
- [Learning Stochastic Dynamical Systems as an Implicit Regularization with Graph Neural Networks](https://mlsanity.com/paper/2307.06097/) (2023)
- [Reconstruction of neuromorphic dynamics from a single scalar time series using variational autoencoder and neural network map](https://mlsanity.com/paper/2411.07055/) (2024)
- [Structural Inference under Hidden Agents](https://mlsanity.com/paper/2609.18045/) (2026)

## Abstract (arXiv)

Many complex processes can be viewed as dynamical systems on networks. However, in real cases, only the performances of the system are known, the network structure and the dynamical rules are not observed. Therefore, recovering latent network structure and dynamics from observed time series data are important tasks because it may help us to open the black box, and even to build up the model of a complex system automatically. Although this problem hosts a wealth of potential applications in biology, earth science, and epidemics etc., conventional methods have limitations. In this work, we introduce a new framework, Gumbel Graph Network (GGN), which is a model-free, data-driven deep learning framework to accomplish the reconstruction of both network connections and the dynamics on it. Our model consists of two jointly trained parts: a network generator that generating a discrete network with the Gumbel Softmax technique; and a dynamics learner that utilizing the generated network and one-step trajectory value to predict the states in future steps. We exhibit the universality of our framework on different kinds of time-series data: with the same structure, our model can be trained to accurately recover the network structure and predict future states on continuous, discrete, and binary dynamics, and outperforms competing network reconstruction methods.