Anonymous Walk Embeddings

TL;DR

This paper introduces anonymous walk embeddings as a scalable, unsupervised method for representing entire graphs, improving classification accuracy over existing CNN and kernel-based methods.

Contribution

It proposes a novel graph embedding approach based on anonymous walks, enabling task-independent, explicit, and distributed graph representations.

Findings

Embedding with anonymous walks improves classification accuracy

Method outperforms traditional graph kernels and CNN-based methods

Scalable unsupervised learning of graph representations

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.