Learning Convolutional Neural Networks for Graphs

Mathias Niepert, Mohamed Ahmed, Konstantin Kutzkov
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:2014-2023, 2016.

Abstract

Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs. These graphs may be undirected, directed, and with both discrete and continuous node and edge attributes. Analogous to image-based convolutional networks that operate on locally connected regions of the input, we present a general approach to extracting locally connected regions from graphs. Using established benchmark data sets, we demonstrate that the learned feature representations are competitive with state of the art graph kernels and that their computation is highly efficient.

Cite this Paper

BibTeX
@InProceedings{pmlr-v48-niepert16, title = {Learning Convolutional Neural Networks for Graphs}, author = {Niepert, Mathias and Ahmed, Mohamed and Kutzkov, Konstantin}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {2014--2023}, year = {2016}, editor = {Balcan, Maria Florina and Weinberger, Kilian Q.}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/niepert16.pdf}, url = {https://proceedings.mlr.press/v48/niepert16.html}, abstract = {Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs. These graphs may be undirected, directed, and with both discrete and continuous node and edge attributes. Analogous to image-based convolutional networks that operate on locally connected regions of the input, we present a general approach to extracting locally connected regions from graphs. Using established benchmark data sets, we demonstrate that the learned feature representations are competitive with state of the art graph kernels and that their computation is highly efficient.} }
Endnote
%0 Conference Paper %T Learning Convolutional Neural Networks for Graphs %A Mathias Niepert %A Mohamed Ahmed %A Konstantin Kutzkov %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-niepert16 %I PMLR %P 2014--2023 %U https://proceedings.mlr.press/v48/niepert16.html %V 48 %X Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs. These graphs may be undirected, directed, and with both discrete and continuous node and edge attributes. Analogous to image-based convolutional networks that operate on locally connected regions of the input, we present a general approach to extracting locally connected regions from graphs. Using established benchmark data sets, we demonstrate that the learned feature representations are competitive with state of the art graph kernels and that their computation is highly efficient.
RIS
TY - CPAPER TI - Learning Convolutional Neural Networks for Graphs AU - Mathias Niepert AU - Mohamed Ahmed AU - Konstantin Kutzkov BT - Proceedings of The 33rd International Conference on Machine Learning DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-niepert16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 48 SP - 2014 EP - 2023 L1 - http://proceedings.mlr.press/v48/niepert16.pdf UR - https://proceedings.mlr.press/v48/niepert16.html AB - Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs. These graphs may be undirected, directed, and with both discrete and continuous node and edge attributes. Analogous to image-based convolutional networks that operate on locally connected regions of the input, we present a general approach to extracting locally connected regions from graphs. Using established benchmark data sets, we demonstrate that the learned feature representations are competitive with state of the art graph kernels and that their computation is highly efficient. ER -
APA
Niepert, M., Ahmed, M. & Kutzkov, K.. (2016). Learning Convolutional Neural Networks for Graphs. Proceedings of The 33rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 48:2014-2023 Available from https://proceedings.mlr.press/v48/niepert16.html.

Related Material