GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → CRIPAC-DIG → H-GCN

CRIPAC-DIG / H-GCN

Licence: MIT license
[IJCAI 2019] Source code and datasets for "Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification"

Programming Languages

python
139335 projects - #7 most used programming language

Labels

machine-learninggraph-neural-networks

Projects that are alternatives of or similar to H-GCN

eeg-gcnn
Resources for the paper titled "EEG-GCNN: Augmenting Electroencephalogram-based Neurological Disease Diagnosis using a Domain-guided Graph Convolutional Neural Network". Accepted for publication (with an oral spotlight!) at ML4H Workshop, NeurIPS 2020.
Stars: ✭ 50 (-51.46%)
Mutual labels:  graph-neural-networks
GNN4CD
Supervised community detection with line graph neural networks
Stars: ✭ 67 (-34.95%)
Mutual labels:  graph-neural-networks
deepsphere-cosmo-tf1
A spherical convolutional neural network for cosmology (TFv1).
Stars: ✭ 119 (+15.53%)
Mutual labels:  graph-neural-networks
KGPool
[ACL 2021] KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction
Stars: ✭ 33 (-67.96%)
Mutual labels:  graph-neural-networks
GraphLIME
This is a Pytorch implementation of GraphLIME
Stars: ✭ 40 (-61.17%)
Mutual labels:  graph-neural-networks
graph-convnet-tsp
Code for the paper 'An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem' (INFORMS Annual Meeting Session 2019)
Stars: ✭ 196 (+90.29%)
Mutual labels:  graph-neural-networks
NBFNet
Official implementation of Neural Bellman-Ford Networks (NeurIPS 2021)
Stars: ✭ 106 (+2.91%)
Mutual labels:  graph-neural-networks
Literatures-on-GNN-Acceleration
A reading list for deep graph learning acceleration.
Stars: ✭ 50 (-51.46%)
Mutual labels:  graph-neural-networks
TIMME
TIMME: Twitter Ideology-detection via Multi-task Multi-relational Embedding (code & data)
Stars: ✭ 57 (-44.66%)
Mutual labels:  graph-neural-networks
awesome-graph-explainability-papers
Papers about explainability of GNNs
Stars: ✭ 153 (+48.54%)
Mutual labels:  graph-neural-networks
graphtrans
Representing Long-Range Context for Graph Neural Networks with Global Attention
Stars: ✭ 45 (-56.31%)
Mutual labels:  graph-neural-networks
Meta-GDN AnomalyDetection
Implementation of TheWebConf 2021 -- Few-shot Network Anomaly Detection via Cross-network Meta-learning
Stars: ✭ 22 (-78.64%)
Mutual labels:  graph-neural-networks
sdn-nfv-papers
This is a paper list about Resource Allocation in Network Functions Virtualization (NFV) and Software-Defined Networking (SDN).
Stars: ✭ 40 (-61.17%)
Mutual labels:  graph-neural-networks
GeometricFlux.jl
Geometric Deep Learning for Flux
Stars: ✭ 288 (+179.61%)
Mutual labels:  graph-neural-networks
InterGCN-ABSA
[COLING 2020] Jointly Learning Aspect-Focused and Inter-Aspect Relations with Graph Convolutional Networks for Aspect Sentiment Analysis
Stars: ✭ 41 (-60.19%)
Mutual labels:  graph-neural-networks
gnn-lspe
Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations), ICLR 2022
Stars: ✭ 165 (+60.19%)
Mutual labels:  graph-neural-networks
GNNSCVulDetector
Smart Contract Vulnerability Detection Using Graph Neural Networks (IJCAI-20 Accepted)
Stars: ✭ 42 (-59.22%)
Mutual labels:  graph-neural-networks
LibAUC
An End-to-End Machine Learning Library to Optimize AUC (AUROC, AUPRC).
Stars: ✭ 115 (+11.65%)
Mutual labels:  graph-neural-networks
RL-based-Graph2Seq-for-NQG
Code & data accompanying the ICLR 2020 paper "Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation"
Stars: ✭ 104 (+0.97%)
Mutual labels:  graph-neural-networks
OpenHGNN
This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL.
Stars: ✭ 264 (+156.31%)
Mutual labels:  graph-neural-networks
View All Similar Projects ➔

H-GCN

Description

This is the repository for the IJCAI-19 paper Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification.

Requirements

  • Tensorflow (1.9.0)
  • networkx

Usage

You can conduct node classification experiments on citation network (Cora, Citeseer or Pubmed) with the following commands:

python train.py --dataset cora --epochs 60 --early_stopping 1000 --coarsen_level 4 --dropout 0.85 --weight_decay 7e-4 --hidden 32 --node_wgt_embed_dim 8 --seed1 156 --seed2 136
python train.py --dataset citeseer --epochs 200 --early_stopping 60 --coarsen_level 4 --dropout 0.85 --weight_decay 7e-4 --hidden 30 --node_wgt_embed_dim 15 --seed1 156 --seed2 156
python train.py --dataset pubmed --epochs 250 --early_stopping 1000 --coarsen_level 4 --dropout 0.85 --weight_decay 7e-4 --hidden 30 --node_wgt_embed_dim 8 --seed1 156 --seed2 136

Cite

Please cite our paper if you use this code in your own work:

@inproceedings{hgcn_ijcai19,
    title = {Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification},
    author = {Fenyu Hu and Yanqiao Zhu and Shu Wu and Liang Wang and Tieniu Tan},
    booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, (IJCAI)},
    year = {2019},
    url = {https://arxiv.org/abs/1902.06667}
}
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].