https://github.com/rusty1s/deep-graph-matching-consensus

Implementation of "Deep Graph Matching Consensus" in PyTorch
https://github.com/rusty1s/deep-graph-matching-consensus

geometric-deep-learning graph-matching graph-neural-networks neighborhood-consensus pytorch

Last synced: 2 days ago
JSON representation

Implementation of "Deep Graph Matching Consensus" in PyTorch

• Host: GitHub
• URL: https://github.com/rusty1s/deep-graph-matching-consensus
• Owner: rusty1s
• License: mit
• Created: 2019-10-02T12:49:39.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2021-09-22T07:10:24.000Z (about 3 years ago)
• Last Synced: 2024-05-09T23:46:03.136Z (5 months ago)
• Topics: geometric-deep-learning, graph-matching, graph-neural-networks, neighborhood-consensus, pytorch
• Language: Python
• Homepage: https://openreview.net/forum?id=HyeJf1HKvS
• Size: 3.5 MB
• Stars: 254
• Watchers: 10
• Forks: 47
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
[build-image]: https://travis-ci.org/rusty1s/deep-graph-matching-consensus.svg?branch=master

[build-url]: https://travis-ci.org/rusty1s/deep-graph-matching-consensus

[docs-image]: https://readthedocs.org/projects/deep-graph-matching-consensus/badge/?version=latest

[docs-url]: https://deep-graph-matching-consensus.readthedocs.io/en/latest/?badge=latest

[coverage-image]: https://codecov.io/gh/rusty1s/deep-graph-matching-consensus/branch/master/graph/badge.svg

[coverage-url]: https://codecov.io/github/rusty1s/deep-graph-matching-consensus?branch=master

Deep Graph Matching Consensus




--------------------------------------------------------------------------------

[![Build Status][build-image]][build-url]

[![Docs Status][docs-image]][docs-url]

[![Code Coverage][coverage-image]][coverage-url]

**[Documentation](https://deep-graph-matching-consensus.readthedocs.io)**

This is a PyTorch implementation of **Deep Graph Matching Consensus**, as described in our paper:

Matthias Fey, Jan E. Lenssen, Christopher Morris, Jonathan Masci, Nils M. Kriege: [Deep Graph Matching Consensus](https://openreview.net/forum?id=HyeJf1HKvS) *(ICLR 2020)*

## Requirements

* **[PyTorch](https://pytorch.org/get-started/locally/)** (>=1.2.0)

* **[PyTorch Geometric](https://github.com/rusty1s/pytorch_geometric)** (>=1.5.0)

* **[KeOps](https://github.com/getkeops/keops)** (>=1.1.0)

## Installation

```

$ python setup.py install

```

Head over to our [documentation](https://deep-graph-matching-consensus.readthedocs.io) for a detailed overview of the `DGMC` module.

## Running examples

We provide training and evaluation procedures for the [PascalVOC with Berkely annotations](https://pytorch-geometric.readthedocs.io/en/latest/modules/datasets.html#torch_geometric.datasets.PascalVOCKeypoints) dataset, the [WILLOW-ObjectClass](https://pytorch-geometric.readthedocs.io/en/latest/modules/datasets.html#torch_geometric.datasets.WILLOWObjectClass) dataset, the [PascalPF](https://pytorch-geometric.readthedocs.io/en/latest/modules/datasets.html#torch_geometric.datasets.PascalPF) dataset, and the [DBP15K](https://pytorch-geometric.readthedocs.io/en/latest/modules/datasets.html#torch_geometric.datasets.DBP15K) dataset.

Experiments can be run via:

```

$ cd examples/

$ python pascal.py

$ python willow.py

$ python pascal_pf.py

$ python dbp15k.py --category=zh_en

```



  

  

  

  



## Cite

Please cite [our paper](https://openreview.net/forum?id=HyeJf1HKvS) if you use this code in your own work:

```

@inproceedings{Fey/etal/2020,

  title={Deep Graph Matching Consensus},

  author={Fey, M. and Lenssen, J. E. and Morris, C. and Masci, J. and Kriege, N. M.},

  booktitle={International Conference on Learning Representations (ICLR)},

  year={2020},

}

```

## Running tests

```

$ python setup.py test

```