• Stars
    star
    126
  • Rank 284,543 (Top 6 %)
  • Language
    Python
  • License
    MIT License
  • Created about 3 years ago
  • Updated almost 2 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

[WWW'22] Towards Unsupervised Deep Graph Structure Learning

Towards Unsupervised Deep Graph Structure Learning

This is the source code of WWW-2022 paper "Towards Unsupervised Deep Graph Structure Learning" (SUBLIME).

The proposed framework

REQUIREMENTS

This code requires the following:

  • Python==3.7
  • PyTorch==1.7.1
  • DGL==0.7.1
  • Numpy==1.20.2
  • Scipy==1.6.3
  • Scikit-learn==0.24.2
  • Munkres==1.1.4
  • ogb==1.3.1

USAGE

Step 1: All the scripts are included in the "scripts" folder. Please get into this folder first.

cd scripts

Step 2: Run the experiments you want:

[Cora]Node classification @ structure inference:

bash cora_si.sh

[Cora]Node classification @ structure refinement:

bash cora_sr.sh

[Cora]Node clustering @ structure refinement:

bash cora_clu.sh

[Citeseer]Node classification @ structure inference:

bash citeseer_si.sh

[Citeseer]Node classification @ structure refinement:

bash citeseer_sr.sh

[Citeseer]Node clustering @ structure refinement:

bash citeseer_clu.sh

[Pubmed]Node classification @ structure inference:

bash pubmed_si.sh

[Pubmed]Node classification @ structure refinement:

bash pubmed_sr.sh

Cite

If you compare with, build on, or use aspects of SUBLIME framework, please cite the following:

@inproceedings{liu2022towards,
  title={Towards unsupervised deep graph structure learning},
  author={Liu, Yixin and Zheng, Yu and Zhang, Daokun and Chen, Hongxu and Peng, Hao and Pan, Shirui},
  booktitle={Proceedings of the ACM Web Conference 2022},
  pages={1392--1403},
  year={2022}
}

More Repositories

1

Awesome-Graph-Neural-Networks

Paper Lists for Graph Neural Networks
2,196
star
2

graph_datasets

A Repository of Benchmark Graph Datasets for Graph Classification (31 Graph Datasets In Total).
282
star
3

ARGA

This is a TensorFlow implementation of the Adversarially Regularized Graph Autoencoder(ARGA) model as described in our paper: Pan, S., Hu, R., Long, G., Jiang, J., Yao, L., & Zhang, C. (2018). Adversarially Regularized Graph Autoencoder for Graph Embedding, [https://www.ijcai.org/proceedings/2018/0362.pdf].
Python
186
star
4

CoLA

[TNNLS] Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
Python
75
star
5

TriDNR

Tri-Party Deep Network Representation, IJCAI-16
Python
72
star
6

MTGODE

[TKDE 2022] The official PyTorch implementation of the paper "Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs".
Python
66
star
7

UDAGCN

Python implementation of "Unsupervised Domain Adaptive Graph Convolutional Networks", WWW-20.
Python
54
star
8

ANEMONE

[CIKM 2021] A PyTorch implementation of "ANEMONE: Graph Anomaly Detection with Multi-Scale Contrastive Learning".
Python
46
star
9

MERIT

[IJCAI 2021] A PyTorch implementation of "Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning".
Python
38
star
10

MGAE

Implementation of the CIKM-17 paper β€œMGAE: Marginalized Graph Autoencoder for Graph Clustering”
MATLAB
28
star
11

graph-deep-learning

This repository summarises the open source codes of our group
27
star
12

OpenWGL

OpenWGL: Open-World Graph Learning, ICDM-2020
Python
5
star
13

MTG

Joint Structure Feature Exploration and Regularization for Multi-Task Graph Classification
Java
3
star
14

BANE

BANE: Binarized Attributed Network Embedding - ICDM2018
MATLAB
2
star