DeepAI AI Chat
Log In Sign Up

Anonymous Walk Embeddings

by   Sergey Ivanov, et al.

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.


page 1

page 2

page 3

page 4


graph2vec: Learning Distributed Representations of Graphs

Recent works on representation learning for graph structured data predom...

Classifying Graphs as Images with Convolutional Neural Networks

The task of graph classification is currently dominated by graph kernels...

DeepMap: Learning Deep Representations for Graph Classification

Graph-structured data arise in many scenarios. A fundamental problem is ...

Ego-CNN: Distributed, Egocentric Representations of Graphs for Detecting Critical Structures

We study the problem of detecting critical structures using a graph embe...

Learning Convolutional Neural Networks for Graphs

Numerous important problems can be framed as learning from graph data. W...

Computing Graph Descriptors on Edge Streams

Graph feature extraction is a fundamental task in graphs analytics. Usin...

Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations

Graph classification is a significant problem in many scientific domains...