GINA: Neural Relational Inference From Independent Snapshots
arXiv:2105.14329
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.
References in corpus (11)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Evolutionary games on graphs
- Modeling polypharmacy side effects with graph convolutional networks
- Controllability of Brain Networks
- High-accuracy approximation of binary-state dynamics on networks
- Model-free inference of direct network interactions from nonlinear collective dynamics
- Estimating network structure from unreliable measurements
- Network comparison and the within-ensemble graph distance
- Designing Complex Networks
- Coupled Map Networks as Communication Schemes
- Maximum-Likelihood Network Reconstruction for SIS Processes is NP-Hard