Persistence Enhanced Graph Neural Network

Qi Zhao, Ze Ye, Chao Chen, Yusu Wang
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108:2896-2906, 2020.

Abstract

Local structural information can increase the adaptability of graph convolutional networks to large graphs with heterogeneous topology. Existing methods only use relatively simplistic topological information, such as node degrees.We present a novel approach leveraging advanced topological information, i.e., persistent homology, which measures the information flow efficiency at different parts of the graph. To fully exploit such structural information in real world graphs, we propose a new network architecture which learns to use persistent homology information to reweight messages passed between graph nodes during convolution. For node classification tasks, our network outperforms existing ones on a broad spectrum of graph benchmarks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v108-zhao20d, title = {Persistence Enhanced Graph Neural Network}, author = {Zhao, Qi and Ye, Ze and Chen, Chao and Wang, Yusu}, booktitle = {Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics}, pages = {2896--2906}, year = {2020}, editor = {Chiappa, Silvia and Calandra, Roberto}, volume = {108}, series = {Proceedings of Machine Learning Research}, month = {26--28 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v108/zhao20d/zhao20d.pdf}, url = {https://proceedings.mlr.press/v108/zhao20d.html}, abstract = {Local structural information can increase the adaptability of graph convolutional networks to large graphs with heterogeneous topology. Existing methods only use relatively simplistic topological information, such as node degrees.We present a novel approach leveraging advanced topological information, i.e., persistent homology, which measures the information flow efficiency at different parts of the graph. To fully exploit such structural information in real world graphs, we propose a new network architecture which learns to use persistent homology information to reweight messages passed between graph nodes during convolution. For node classification tasks, our network outperforms existing ones on a broad spectrum of graph benchmarks.} }
Endnote
%0 Conference Paper %T Persistence Enhanced Graph Neural Network %A Qi Zhao %A Ze Ye %A Chao Chen %A Yusu Wang %B Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2020 %E Silvia Chiappa %E Roberto Calandra %F pmlr-v108-zhao20d %I PMLR %P 2896--2906 %U https://proceedings.mlr.press/v108/zhao20d.html %V 108 %X Local structural information can increase the adaptability of graph convolutional networks to large graphs with heterogeneous topology. Existing methods only use relatively simplistic topological information, such as node degrees.We present a novel approach leveraging advanced topological information, i.e., persistent homology, which measures the information flow efficiency at different parts of the graph. To fully exploit such structural information in real world graphs, we propose a new network architecture which learns to use persistent homology information to reweight messages passed between graph nodes during convolution. For node classification tasks, our network outperforms existing ones on a broad spectrum of graph benchmarks.
APA
Zhao, Q., Ye, Z., Chen, C. & Wang, Y.. (2020). Persistence Enhanced Graph Neural Network. Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 108:2896-2906 Available from https://proceedings.mlr.press/v108/zhao20d.html.

Related Material