Data

Tools

Indexes

Applications

Experiments

Open Source Science

how_attentive_are_gats

Code for the paper "How Attentive are Graph Attention Networks?" (ICLR'2022)

https://github.com/tech-srl/how_attentive_are_gats

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.8%) to scientific vocabulary

Keywords

are attention attentive gat gatv2 graph graph-attention-networks graph-neural-networks how networks pytorch
Last synced: 6 months ago · JSON representation ·

Repository

Code for the paper "How Attentive are Graph Attention Networks?" (ICLR'2022)

Basic Info
  • Host: GitHub
  • Owner: tech-srl
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 3.34 MB
Statistics
  • Stars: 340
  • Watchers: 11
  • Forks: 41
  • Open Issues: 4
  • Releases: 0
Topics
are attention attentive gat gatv2 graph graph-attention-networks graph-neural-networks how networks pytorch
Created over 4 years ago · Last pushed almost 4 years ago
Metadata Files
Readme Citation

README.md

How Attentive are Graph Attention Networks?

This repository is the official implementation of How Attentive are Graph Attention Networks?.

January 2022: the paper was accepted to ICLR'2022 !

alt text

Using GATv2

GATv2 is now available as part of PyTorch Geometric library! from torch_geometric.nn.conv.gatv2_conv import GATv2Conv

https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#torch_geometric.nn.conv.GATv2Conv

and also is in this main directory.

GATv2 is now available as part of DGL library! from dgl.nn.pytorch import GATv2Conv

https://docs.dgl.ai/en/latest/api/python/nn.pytorch.html#gatv2conv

and also in this repository.

GATv2 is now available as part of Google's TensorFlow GNN library! from tensorflow_gnn.graph.keras.layers.gat_v2 import GATv2Convolution

https://github.com/tensorflow/gnn/blob/main/tensorflowgnn/docs/apidocs/python/gnn/keras/layers/GATv2.md

Code Structure

Since our experiments (Section 4) are based on different frameworks, this repository is divided into several sub-projects: 1. The subdirectory arxiv_mag_products_collab_citation2_noise contains the needed files to reproduce the results of Node-Prediction, Link-Prediction, and Robustness to Noise (Tables 2a, 3 and Figure 4). 2. The subdirectory proteins contains the needed files to reproduce the results of ogbn-proteins in Node-Prediction (Table 2b). 3. The subdirectory dictionary_lookup contains the need files to reproduce the results of the DictionaryLookup benchmark (Figure 3). 4. The subdirectory tf-gnn-samples contains the needed files to reproduce the results of the VarMisuse and QM9 datasets (Table 1 and Table 4).

Requirements

Each subdirectory contains its own requirements and dependencies.

Generally, all subdirectories depend on PyTorch 1.7.1 and PyTorch Geometric version 1.7.0 (proteins depends on DGL version 0.6.0). The subdirectory tf-gnn-samples (VarMisuse and QM9) depends on TensorFlow 1.13.

Hardware

In general, all experiments can run on either GPU or CPU.

Citation

How Attentive are Graph Attention Networks? @inproceedings{ brody2022how, title={How Attentive are Graph Attention Networks? }, author={Shaked Brody and Uri Alon and Eran Yahav}, booktitle={International Conference on Learning Representations}, year={2022}, url={https://openreview.net/forum?id=F72ximsx7C1} }

Owner

  • Name: tech-srl
  • Login: tech-srl
  • Kind: organization

Citation (CITATION.cff) 

@inproceedings{
  brody2022how,
  title={How Attentive are Graph Attention Networks? },
  author={Shaked Brody and Uri Alon and Eran Yahav},
  booktitle={International Conference on Learning Representations},
  year={2022},
  url={https://openreview.net/forum?id=F72ximsx7C1}
}

GitHub Events

Total
  • Issues event: 1
  • Watch event: 40
  • Fork event: 5
Last Year
  • Issues event: 1
  • Watch event: 40
  • Fork event: 5

Committers

Last synced: 8 months ago

All Time
  • Total Commits: 27
  • Total Committers: 3
  • Avg Commits per committer: 9.0
  • Development Distribution Score (DDS): 0.37
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
urialon u****1@g****m 17
Shaked Brody s****r@g****m 9
Uri Alon u****n@t****h 1
Committer Domains (Top 20 + Academic)
tir-1-18.eth: 1

Issues and Pull Requests

Last synced: 8 months ago

All Time
  • Total issues: 8
  • Total pull requests: 0
  • Average time to close issues: 2 months
  • Average time to close pull requests: N/A
  • Total issue authors: 7
  • Total pull request authors: 0
  • Average comments per issue: 2.25
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • adrianjav (2)
  • wenhaozheng-nju (1)
  • LeadBeetle (1)
  • JiaYingjuan (1)
  • ALEX13679173326 (1)
  • Jonbroad15 (1)
  • Zhayuanhe (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

arxiv_mag_products_collab_citation2_noise/requirements.txt pypi
  • ogb >=1.3.1
  • torch >=1.7.1
  • torch-geometric >=1.7.0
  • torch-scatter >=2.0.4
  • torch-sparse >=0.6.0
  • tqdm >=4.42.1
dictionary_lookup/requirements.txt pypi
  • attrdict ==2.0.1
  • seaborn *
  • sklearn *
  • torch >=1.7.1
  • torch-geometric >=1.7.0
  • torch-scatter >=2.0.4
  • torch-sparse >=0.6.0
  • torchvision *
proteins/requirements.txt pypi
  • dgl ==0.6.0
  • ogb >=1.3.1
  • torch >=1.7.1
  • tqdm >=4.42.1
tf-gnn-samples/requirements.txt pypi
  • docopt *
  • dpu-utils >=0.1.30
  • numpy *
  • tensorflow-gpu >=1.13.1