# GINA: Neural Relational Inference From Independent Snapshots

arXiv: https://arxiv.org/abs/2105.14329 · HTML: https://mlsanity.com/paper/2105.14329/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 47 references that are in the map.
- First posted on arXiv 29 May 2021.

## Builds on (most cited first, 9 of 9)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Neural Relational Inference for Interacting Systems](https://mlsanity.com/paper/1802.04687/) (2018)
- [Modeling polypharmacy side effects with graph convolutional networks](https://mlsanity.com/paper/1802.00543/) (2018)
- [A General Deep Learning Framework for Network Reconstruction and Dynamics Learning](https://mlsanity.com/paper/1812.11482/) (2018)
- [Controllability of Brain Networks](https://mlsanity.com/paper/1406.5197/) (2014)
- [Connectivity Inference from Neural Recording Data: Challenges, Mathematical Bases and Research Directions](https://mlsanity.com/paper/1708.01888/) (2017)
- [Network comparison and the within-ensemble graph distance](https://mlsanity.com/paper/2008.02415/) (2020)
- [Estimating network structure from unreliable measurements](https://mlsanity.com/paper/1803.02427/) (2018)
- [Reducing Spreading Processes on Networks to Markov Population Models](https://mlsanity.com/paper/1906.11508/) (2019)

## Abstract (arXiv)

Dynamical systems in which local interactions among agents give rise to complex emerging phenomena are ubiquitous in nature and society. This work explores the problem of inferring the unknown interaction structure (represented as a graph) of such a system from measurements of its constituent agents or individual components (represented as nodes). We consider a setting where the underlying dynamical model is unknown and where different measurements (i.e., snapshots) may be independent (e.g., may stem from different experiments). We propose GINA (Graph Inference Network Architecture), a graph neural network (GNN) to simultaneously learn the latent interaction graph and, conditioned on the interaction graph, the prediction of a node's observable state based on adjacent vertices. GINA is based on the hypothesis that the ground truth interaction graph -- among all other potential graphs -- allows to predict the state of a node, given the states of its neighbors, with the highest accuracy. We test this hypothesis and demonstrate GINA's effectiveness on a wide range of interaction graphs and dynamical processes.