search

A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anom

Link:https://arxiv.org/pdf/2307.03759.pdfarrow-up-right

hashtag
Abstract

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. Alt text

PreviousSensor DataNextBig Data Driven Marine Environment Information Forecasting: A Time Series Prediction Network

Last updated