Anonymous Walk Embeddings

Sergey Ivanov, Evgeny Burnaev
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:2186-2195, 2018.

Abstract

The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data. While CNNs demonstrate state-of-the-art performance in graph classification task, such methods are supervised and therefore steer away from the original problem of network representation in task-agnostic manner. Here, we coherently propose an approach for embedding entire graphs and show that our feature representations with SVM classifier increase classification accuracy of CNN algorithms and traditional graph kernels. For this we describe a recently discovered graph object, anonymous walk, on which we design task-independent algorithms for learning graph representations in explicit and distributed way. Overall, our work represents a new scalable unsupervised learning of state-of-the-art representations of entire graphs.

Cite this Paper

BibTeX
@InProceedings{pmlr-v80-ivanov18a, title = {Anonymous Walk Embeddings}, author = {Ivanov, Sergey and Burnaev, Evgeny}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {2186--2195}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/ivanov18a/ivanov18a.pdf}, url = {https://proceedings.mlr.press/v80/ivanov18a.html}, abstract = {The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data. While CNNs demonstrate state-of-the-art performance in graph classification task, such methods are supervised and therefore steer away from the original problem of network representation in task-agnostic manner. Here, we coherently propose an approach for embedding entire graphs and show that our feature representations with SVM classifier increase classification accuracy of CNN algorithms and traditional graph kernels. For this we describe a recently discovered graph object, anonymous walk, on which we design task-independent algorithms for learning graph representations in explicit and distributed way. Overall, our work represents a new scalable unsupervised learning of state-of-the-art representations of entire graphs.} }
Endnote
%0 Conference Paper %T Anonymous Walk Embeddings %A Sergey Ivanov %A Evgeny Burnaev %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-ivanov18a %I PMLR %P 2186--2195 %U https://proceedings.mlr.press/v80/ivanov18a.html %V 80 %X The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data. While CNNs demonstrate state-of-the-art performance in graph classification task, such methods are supervised and therefore steer away from the original problem of network representation in task-agnostic manner. Here, we coherently propose an approach for embedding entire graphs and show that our feature representations with SVM classifier increase classification accuracy of CNN algorithms and traditional graph kernels. For this we describe a recently discovered graph object, anonymous walk, on which we design task-independent algorithms for learning graph representations in explicit and distributed way. Overall, our work represents a new scalable unsupervised learning of state-of-the-art representations of entire graphs.
APA
Ivanov, S. & Burnaev, E.. (2018). Anonymous Walk Embeddings. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:2186-2195 Available from https://proceedings.mlr.press/v80/ivanov18a.html.

Related Material