TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Node Classification	Brazil Air-Traffic	GAT (Velickovic et al., 2018)	Accuracy	0.382	# 7
Graph Classification	CIFAR10 100k	GAT	Accuracy (%)	65.48	# 5
Node Classification	Citeseer	GAT	Accuracy	72.5%	# 19
Node Classification	Citeseer	GAT	Training Split	fixed 20 per node	# 1
Node Classification	Citeseer	GAT	Validation	YES	# 1
Node Classification	CiteSeer (0.5%)	GAT	Accuracy	38.2%	# 14
Node Classification	CiteSeer (1%)	GAT	Accuracy	46.5%	# 14
Node Classification	CiteSeer with Public Split: fixed 20 nodes per class	GAT	Accuracy	72.5%	# 15
Node Classification	Cora	GAT	Accuracy	83.0%	# 23
Node Classification	Cora	GAT	Training Split	fixed 20 per node	# 1
Node Classification	Cora	GAT	Validation	YES	# 1
Document Classification	Cora	GAT	Accuracy	83.0%	# 3
Node Classification	Cora (0.5%)	GAT	Accuracy	41.4%	# 13
Node Classification	Cora (1%)	GAT	Accuracy	48.6%	# 13
Node Classification	Cora (3%)	GAT	Accuracy	56.8%	# 15
Node Classification	Cora with Public Split: fixed 20 nodes per class	GAT	Accuracy	83.0%	# 15
Node Classification	Europe Air-Traffic	GAT (Velickovic et al., 2018)	Accuracy	42.4	# 4
Node Classification	Flickr	GAT (Velickovic et al., 2018)	Accuracy	0.359	# 6
Skeleton Based Action Recognition	J-HMBD Early Action	GAT	10%	58.1	# 2
Graph Regression	Lipophilicity	GAT	RMSE	0.950	# 9
Node Classification	PATTERN 100k	GAT	Accuracy (%)	75.824	# 7
Node Classification	PPI	GAT	F1	97.3	# 12
Node Classification	Pubmed	GAT	Accuracy	79.00%	# 27
Node Classification	Pubmed	GAT	Training Split	fixed 20 per node	# 1
Node Classification	Pubmed	GAT	Validation	YES	# 1
Node Classification	PubMed (0.03%)	GAT	Accuracy	50.9%	# 13
Node Classification	PubMed (0.05%)	GAT	Accuracy	50.4%	# 14
Node Classification	PubMed (0.1%)	GAT	Accuracy	59.6%	# 13
Node Classification	PubMed with Public Split: fixed 20 nodes per class	GAT	Accuracy	79.0%	# 17
Node Classification	USA Air-Traffic	GAT (Velickovic et al., 2018)	Accuracy	58.5	# 2
Node Classification	Wiki-Vote	GAT (Velickovic et al., 2018)	Accuracy	59.4	# 2
Graph Regression	ZINC 100k	GAT	MAE	0.463	# 7
Graph Regression	ZINC-500k	GAT	MAE	0.384	# 11

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/skeleton-based-action-recognition-on-j-hmbd)](https://paperswithcode.com/sota/skeleton-based-action-recognition-on-j-hmbd?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-usa-air-traffic)](https://paperswithcode.com/sota/node-classification-on-usa-air-traffic?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-wiki-vote)](https://paperswithcode.com/sota/node-classification-on-wiki-vote?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/document-classification-on-cora)](https://paperswithcode.com/sota/document-classification-on-cora?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-europe-air-traffic)](https://paperswithcode.com/sota/node-classification-on-europe-air-traffic?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/graph-classification-on-cifar10-100k)](https://paperswithcode.com/sota/graph-classification-on-cifar10-100k?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-flickr)](https://paperswithcode.com/sota/node-classification-on-flickr?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-brazil-air-traffic)](https://paperswithcode.com/sota/node-classification-on-brazil-air-traffic?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-pattern-100k)](https://paperswithcode.com/sota/node-classification-on-pattern-100k?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/graph-regression-on-zinc-100k)](https://paperswithcode.com/sota/graph-regression-on-zinc-100k?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/graph-regression-on-lipophilicity)](https://paperswithcode.com/sota/graph-regression-on-lipophilicity?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/graph-regression-on-zinc-500k)](https://paperswithcode.com/sota/graph-regression-on-zinc-500k?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-ppi)](https://paperswithcode.com/sota/node-classification-on-ppi?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-cora-05)](https://paperswithcode.com/sota/node-classification-on-cora-05?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-cora-1)](https://paperswithcode.com/sota/node-classification-on-cora-1?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-pubmed-003)](https://paperswithcode.com/sota/node-classification-on-pubmed-003?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-pubmed-01)](https://paperswithcode.com/sota/node-classification-on-pubmed-01?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-citeseer-05)](https://paperswithcode.com/sota/node-classification-on-citeseer-05?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-citeseer-1)](https://paperswithcode.com/sota/node-classification-on-citeseer-1?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-pubmed-005)](https://paperswithcode.com/sota/node-classification-on-pubmed-005?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-citeseer-with-public)](https://paperswithcode.com/sota/node-classification-on-citeseer-with-public?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-cora-3)](https://paperswithcode.com/sota/node-classification-on-cora-3?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-cora-with-public-split)](https://paperswithcode.com/sota/node-classification-on-cora-with-public-split?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-pubmed-with-public)](https://paperswithcode.com/sota/node-classification-on-pubmed-with-public?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-citeseer)](https://paperswithcode.com/sota/node-classification-on-citeseer?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-cora)](https://paperswithcode.com/sota/node-classification-on-cora?p=graph-attention-networks)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/graph-attention-networks/node-classification-on-pubmed)](https://paperswithcode.com/sota/node-classification-on-pubmed?p=graph-attention-networks)`

Graph Attention Networks

ICLR 2018 • Petar Veličković • Guillem Cucurull • Arantxa Casanova • Adriana Romero • Pietro Liò • Yoshua Bengio

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront... (read more)

PDF Abstract ICLR 2018 PDF ICLR 2018 Abstract

Code

Add Remove Mark official

PetarV-/GAT official

1,855

aymericdamien/TopDeepLearning

5,175

Diego999/pyGAT

1,428

gordicaleksa/pytorch-GAT

842

shenweichen/GraphNeuralNetwork

386

See all 56 implementations

Tasks

Add Remove

DOCUMENT CLASSIFICATION

GRAPH CLASSIFICATION

GRAPH EMBEDDING

GRAPH REGRESSION

LINK PREDICTION

NODE CLASSIFICATION

SKELETON BASED ACTION RECOGNITION

Datasets

Pubmed

Results from the Paper

Edit

Ranked #2 on Node Classification on Wiki-Vote

Get a GitHub badge

TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	BENCHMARK
Graph Classification	CIFAR10 100k	GAT	Accuracy (%)	65.48	# 5	Compare
Node Classification	Citeseer	GAT	Accuracy	72.5%	# 19	Compare
			Training Split	fixed 20 per node	# 1	Compare
			Validation	YES	# 1	Compare
Node Classification	CiteSeer (0.5%)	GAT	Accuracy	38.2%	# 14	Compare
Node Classification	CiteSeer (1%)	GAT	Accuracy	46.5%	# 14	Compare
Node Classification	CiteSeer with Public Split: fixed 20 nodes per class	GAT	Accuracy	72.5%	# 15	Compare
Node Classification	Cora	GAT	Accuracy	83.0%	# 23	Compare
			Training Split	fixed 20 per node	# 1	Compare
			Validation	YES	# 1	Compare
Document Classification	Cora	GAT	Accuracy	83.0%	# 3	Compare
Node Classification	Cora (0.5%)	GAT	Accuracy	41.4%	# 13	Compare
Node Classification	Cora (1%)	GAT	Accuracy	48.6%	# 13	Compare
Node Classification	Cora (3%)	GAT	Accuracy	56.8%	# 15	Compare
Node Classification	Cora with Public Split: fixed 20 nodes per class	GAT	Accuracy	83.0%	# 15	Compare
Skeleton Based Action Recognition	J-HMBD Early Action	GAT	10%	58.1	# 2	Compare
Graph Regression	Lipophilicity	GAT	RMSE	0.950	# 9	Compare
Node Classification	PATTERN 100k	GAT	Accuracy (%)	75.824	# 7	Compare
Node Classification	PPI	GAT	F1	97.3	# 12	Compare
Node Classification	Pubmed	GAT	Accuracy	79.00%	# 27	Compare
			Training Split	fixed 20 per node	# 1	Compare
			Validation	YES	# 1	Compare
Node Classification	PubMed (0.03%)	GAT	Accuracy	50.9%	# 13	Compare
Node Classification	PubMed (0.05%)	GAT	Accuracy	50.4%	# 14	Compare
Node Classification	PubMed (0.1%)	GAT	Accuracy	59.6%	# 13	Compare
Node Classification	PubMed with Public Split: fixed 20 nodes per class	GAT	Accuracy	79.0%	# 17	Compare
Graph Regression	ZINC 100k	GAT	MAE	0.463	# 7	Compare
Graph Regression	ZINC-500k	GAT	MAE	0.384	# 11	Compare

Results from Other Papers

TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	COMPARE
Node Classification	Brazil Air-Traffic	GAT (Velickovic et al., 2018)	Accuracy	0.382	# 7	See all
Node Classification	Europe Air-Traffic	GAT (Velickovic et al., 2018)	Accuracy	42.4	# 4	See all
Node Classification	Flickr	GAT (Velickovic et al., 2018)	Accuracy	0.359	# 6	See all
Node Classification	USA Air-Traffic	GAT (Velickovic et al., 2018)	Accuracy	58.5	# 2	See all
Node Classification	Wiki-Vote	GAT (Velickovic et al., 2018)	Accuracy	59.4	# 2	See all

Methods used in the Paper

Add Remove

METHOD	TYPE
GAT	Graph Models

Graph Attention Networks

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit