MTGNN

SEEDLING This note was planted but not so much effort has been put into it. This seedling requires some nurturing.
reading/mtgnn.md Current Note ID: The unique ID of this note.
#graph neural network #graph #forecasting #time series

This article lists some key ideas of the MTGNN paper.

Key Components

Time Convolution (TC) Module

Time Convolution
The temporal convolution is responsible for capturing temporal patterns in a sequence.

Graph Convolution Module

Mix-hop Propagation in GNN
Mix-hop is a strategy to avoid oversmoothing in GNN

Graph Structure Learning Layer

Graph Structure Learning in GNN
We can learn a graph structure without prior knowledge

Architecture

Wu et al., 2020

Wu et al., 2020

Planted: by ;

References:
  1. Wu2020 Wu Z, Pan S, Long G, Jiang J, Chang X, Zhang C. Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks. arXiv [cs.LG]. 2020. Available: http://arxiv.org/abs/2005.11650
  2. Lässig2021 Lässig F. Temporal Convolutional Networks and Forecasting. In: Unit8 [Internet]. 6 Jul 2021 [cited 28 Nov 2022]. Available: https://unit8.com/resources/temporal-convolutional-networks-and-forecasting/
Similar Articles:
StemGNN
What problem is StemGNN solving: intra-series temporal pattern: DFT Each series inter-series …
Over-Smoothing in Graph Neural Networks
Over-smoothing is the problem that the representations on each node of the graph neural networks …
Box-Cox Transformation
The Box-Cox transformation transforms data into Gaussian data, which is especially useful in feature …
Popularity versus similarity in growing networks
Introduce geometry into the manifold of complex networks
Additional Double Backet Links:
Time Convolution
The temporal convolution is responsible for capturing temporal patterns in a sequence.
Mix-hop Propagation in GNN
Mix-hop is a strategy to avoid oversmoothing in GNN
Graph Structure Learning in GNN
We can learn a graph structure without prior knowledge

L Ma (2022). 'MTGNN', Datumorphism, 11 April. Available at: https://datumorphism.leima.is/reading/mtgnn/.