https://github.com/mdeff/paper-cnn-graph-recurrent-iclr2017
Structured Sequence Modeling with Graph Convolutional Recurrent Networks
https://github.com/mdeff/paper-cnn-graph-recurrent-iclr2017
Last synced: 4 months ago
JSON representation
Structured Sequence Modeling with Graph Convolutional Recurrent Networks
- Host: GitHub
- URL: https://github.com/mdeff/paper-cnn-graph-recurrent-iclr2017
- Owner: mdeff
- License: cc-by-4.0
- Created: 2020-06-09T16:24:27.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2021-01-02T00:23:48.000Z (over 5 years ago)
- Last Synced: 2025-03-16T01:13:21.623Z (about 1 year ago)
- Language: TeX
- Homepage: https://arxiv.org/abs/1612.07659
- Size: 5.19 MB
- Stars: 6
- Watchers: 3
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# Structured Sequence Modeling with Graph Convolutional Recurrent Networks
[Youngjoo Seo](https://www.linkedin.com/in/youngjooseo),
[Michaël Defferrard](https://deff.ch),
[Pierre Vandergheynst](https://people.epfl.ch/pierre.vandergheynst),
[Xavier Bresson](https://www.ntu.edu.sg/home/xbresson), \
International Conference on Neural Information Processing (ICONIP), 2017.
> This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data.
> Precisely, GCRN is a generalization of classical recurrent neural networks (RNN) to data structured by an arbitrary graph.
> Such structured sequences can represent series of frames in videos, spatio-temporal measurements on a network of sensors, or random walks on a vocabulary graph for natural language modeling.
> The proposed model combines convolutional neural networks (CNN) on graphs to identify spatial structures and RNN to find dynamic patterns.
> We study two possible architectures of GCRN, and apply the models to two practical problems: predicting moving MNIST data, and modeling natural language with the Penn Treebank dataset.
> Experiments show that exploiting simultaneously graph spatial and dynamic information about data can improve both precision and learning speed.
```
@inproceedings{gcrn,
title = {Structured Sequence Modeling with Graph Convolutional Recurrent Networks},
author = {Seo, Youngjoo and Defferrard, Micha\"el and Vandergheynst, Pierre and Bresson, Xavier},
booktitle = {International Conference on Neural Information Processing (ICONIP)},
year = {2017},
archiveprefix = {arXiv},
eprint = {1612.07659},
url = {https://arxiv.org/abs/1612.07659},
}
```
## Resources
PDF available at [arXiv], [OpenReview], [ICONIP], [EPFL].
Related: [code], [slides].
[arXiv]: https://arxiv.org/abs/1612.07659
[OpenReview]: https://openreview.net/forum?id=S19eAF9ee
[ICONIP]: https://doi.org/10.1007/978-3-030-04167-0_33
[EPFL]: https://infoscience.epfl.ch/record/227513
[code]: https://github.com/youngjoo-epfl/gconvRNN
[slides]: https://doi.org/10.5281/zenodo.1318401
## Compilation
Compile the latex source into a PDF with `make`.
Run `make clean` to remove temporary files and `make arxiv.zip` to prepare an archive to be uploaded on arXiv.
## Figures
All the figures are in the [`figures`](figures/) folder.
PDFs can be generated with `make figures`.