GINA: Neural Relational Inference From Independent Snapshots

TL;DR

GINA is a neural network approach that infers the underlying interaction graph of a dynamical system from independent snapshots, enabling accurate prediction of node states based on learned interactions.

Contribution

GINA introduces a novel graph neural network architecture that simultaneously infers the interaction graph and predicts node states from independent measurements.

Findings

GINA accurately infers interaction graphs across various dynamical systems.

GINA outperforms baseline methods in predicting node states.

The method works with independent snapshots from different experiments.

Abstract

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.