MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Nazanin Alipourfard, Kristina Lerman, Hrayr Harutyunyan, Greg Ver Steeg, Aram Galstyan
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:21-29, 2019.

Abstract

Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mixing relationships. To address this weakness, we propose a new model, MixHop, that can learn these relationships, including difference operators, by repeatedly mixing feature representations of neighbors at various distances. MixHop requires no additional memory or computational complexity, and outperforms on challenging baselines. In addition, we propose sparsity regularization that allows us to visualize how the network prioritizes neighborhood information across different graph datasets. Our analysis of the learned architectures reveals that neighborhood mixing varies per datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-abu-el-haija19a, title = {{M}ix{H}op: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing}, author = {Abu-El-Haija, Sami and Perozzi, Bryan and Kapoor, Amol and Alipourfard, Nazanin and Lerman, Kristina and Harutyunyan, Hrayr and Steeg, Greg Ver and Galstyan, Aram}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {21--29}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/abu-el-haija19a/abu-el-haija19a.pdf}, url = {https://proceedings.mlr.press/v97/abu-el-haija19a.html}, abstract = {Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mixing relationships. To address this weakness, we propose a new model, MixHop, that can learn these relationships, including difference operators, by repeatedly mixing feature representations of neighbors at various distances. MixHop requires no additional memory or computational complexity, and outperforms on challenging baselines. In addition, we propose sparsity regularization that allows us to visualize how the network prioritizes neighborhood information across different graph datasets. Our analysis of the learned architectures reveals that neighborhood mixing varies per datasets.} }
Endnote
%0 Conference Paper %T MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing %A Sami Abu-El-Haija %A Bryan Perozzi %A Amol Kapoor %A Nazanin Alipourfard %A Kristina Lerman %A Hrayr Harutyunyan %A Greg Ver Steeg %A Aram Galstyan %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-abu-el-haija19a %I PMLR %P 21--29 %U https://proceedings.mlr.press/v97/abu-el-haija19a.html %V 97 %X Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mixing relationships. To address this weakness, we propose a new model, MixHop, that can learn these relationships, including difference operators, by repeatedly mixing feature representations of neighbors at various distances. MixHop requires no additional memory or computational complexity, and outperforms on challenging baselines. In addition, we propose sparsity regularization that allows us to visualize how the network prioritizes neighborhood information across different graph datasets. Our analysis of the learned architectures reveals that neighborhood mixing varies per datasets.
APA
Abu-El-Haija, S., Perozzi, B., Kapoor, A., Alipourfard, N., Lerman, K., Harutyunyan, H., Steeg, G.V. & Galstyan, A.. (2019). MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:21-29 Available from https://proceedings.mlr.press/v97/abu-el-haija19a.html.

Related Material