An Unpooling Layer for Graph Generation

Yinglong Guo, Dongmian Zou, Gilad Lerman
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:3179-3209, 2023.

Abstract

We propose a novel and trainable graph unpooling layer for effective graph generation. The unpooling layer receives an input graph with features and outputs an enlarged graph with desired structure and features. We prove that the output graph of the unpooling layer remains connected and for any connected graph there exists a series of unpooling layers that can produce it from a 3-node graph. We apply the unpooling layer within the generator of a generative adversarial network as well as the decoder of a variational autoencoder. We give extensive experimental evidence demonstrating the competitive performance of our proposed method on synthetic and real data.

Cite this Paper

BibTeX
@InProceedings{pmlr-v206-guo23a, title = {An Unpooling Layer for Graph Generation}, author = {Guo, Yinglong and Zou, Dongmian and Lerman, Gilad}, booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics}, pages = {3179--3209}, year = {2023}, editor = {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem}, volume = {206}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v206/guo23a/guo23a.pdf}, url = {https://proceedings.mlr.press/v206/guo23a.html}, abstract = {We propose a novel and trainable graph unpooling layer for effective graph generation. The unpooling layer receives an input graph with features and outputs an enlarged graph with desired structure and features. We prove that the output graph of the unpooling layer remains connected and for any connected graph there exists a series of unpooling layers that can produce it from a 3-node graph. We apply the unpooling layer within the generator of a generative adversarial network as well as the decoder of a variational autoencoder. We give extensive experimental evidence demonstrating the competitive performance of our proposed method on synthetic and real data.} }
Endnote
%0 Conference Paper %T An Unpooling Layer for Graph Generation %A Yinglong Guo %A Dongmian Zou %A Gilad Lerman %B Proceedings of The 26th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2023 %E Francisco Ruiz %E Jennifer Dy %E Jan-Willem van de Meent %F pmlr-v206-guo23a %I PMLR %P 3179--3209 %U https://proceedings.mlr.press/v206/guo23a.html %V 206 %X We propose a novel and trainable graph unpooling layer for effective graph generation. The unpooling layer receives an input graph with features and outputs an enlarged graph with desired structure and features. We prove that the output graph of the unpooling layer remains connected and for any connected graph there exists a series of unpooling layers that can produce it from a 3-node graph. We apply the unpooling layer within the generator of a generative adversarial network as well as the decoder of a variational autoencoder. We give extensive experimental evidence demonstrating the competitive performance of our proposed method on synthetic and real data.
APA
Guo, Y., Zou, D. & Lerman, G.. (2023). An Unpooling Layer for Graph Generation. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 206:3179-3209 Available from https://proceedings.mlr.press/v206/guo23a.html.

Related Material