A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anom
PreviousSensor DataNextBig Data Driven Marine Environment Information Forecasting: A Time Series Prediction Network
Last updated
Last updated
Link:https://arxiv.org/pdf/2307.03759.pdf
Key con of DL like RNN, CNN, Transformer: do not explicitly model the spatial relations existing between time series in non-Euclidean space.
GNN can overcome this.