Forecasting Unobserved Node States with spatio-temporal Graph Neural Networks.

Andreas Roth Thomas Liebig

Published in: CoRR (2022)

Keyphrases

spatio temporal
neural network
graph structure
directed graph
short term
undirected graph
backpropagation neural networks
spatial and temporal
betweenness centrality
graph representation

nodes of a graph
pattern recognition
edge weights
random walk
fuzzy logic
finding the shortest path
image sequences
genetic algorithm
graph model
weighted graph

graph theory
fault diagnosis
moving objects
bipartite graph
graph matching
overlapping communities
artificial neural networks
path length
directed acyclic graph
graph mining

connected components
graph databases
back propagation
long term
feed forward
self organizing maps
action recognition
strongly connected
partially observed
neural nets