Dynamics Based Features For Graph Classification

Abstract

Numerous social, medical, engineering and biological challenges can be framed as graph-based learning tasks. Here, we propose a new feature based approach to network classification. We show how dynamics on a network can be useful to reveal patterns about the organization of the components of the underlying graph where the process takes place. We define generalized assortativities on networks and use them as generalized features across multiple time scales. These features turn out to be suitable signatures for discriminating between different classes of networks. Our method is evaluated empirically on established network benchmarks. We also introduce a new dataset of human brain networks (connectomes) and use it to evaluate our method. Results reveal that our dynamics based features are competitive and often outperform state of the art accuracies.

This paper is under review as a conference paper at ECML-PKDD 2017

References in corpus (5)

• Modularity and community structure in networks
• Learning Convolutional Neural Networks for Graphs
• Random Walks, Markov Processes and the Multiscale Modular Organization of Complex Networks
• Laplacian Dynamics and Multiscale Modular Structure in Networks
• The stability of a graph partition: A dynamics-based framework for community detection

Cited by in corpus (7)

• Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization
• A Simple Baseline Algorithm for Graph Classification
• Walk-Steered Convolution for Graph Classification
• When Work Matters: Transforming Classical Network Structures to Graph CNN
• Variational Recurrent Neural Networks for Graph Classification
• Gaussian-Induced Convolution for Graphs
• Using Laplacian Spectrum as Graph Feature Representation