Skip to main content

Table 11 Summary of Graph Neural Networks with application area, graph structure, type, task, and model used

From: A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions

Refs.

Application

Graph structure

Graph type

Graph task

GNN model used

[88]

(2020)

1. Recurrent Graph Neural Networks for Text Classification

Structural data

Static Graph

Node Classification

Text GCN

RGNN

[68]

(2021)

1. Machine translation

2. Natural language generation

3. Information extraction

4. Semantic parsing

Structural data

Static Graph

Node & Edge Level task

Graph2seq

Graph2tree

Graph2graph

[16]

(2019)

1. Multi-hop Reading Comprehension

Structural data

Heterogeneous Graphs

Edge Level task

GCN

[89]

(2020)

1. Edge masking

Structural data

Undirected Graph

Edge Level task

LSTM + GNN

[90]

(2020)

1. Multi-hop reading comprehension on hotpot a Fact verification on FEVER

Structural data

Directed Graph

Node level task

GCN