In this paper, we present a general framework to estimate the network entropy that is represented by means of an undirected graph and subsequently employ this framework for graph classification tasks. The proposed framework is based on local information functionals which are defined using induced connected subgraphs of different sizes. These induced subgraphs are termed graphlets. Specifically, we extract the set of all graphlets of a specific sizes and compute the graph entropy using our proposed framework. To classify the network into different categories, we construct a feature vector whose components are obtained by computing entropies of different graphlet sizes. We apply the proposed framework to two different tasks, namely view-based object recognition and biomedical datasets with binary outcomes classification. Finally, we report and compare the classification accuracies of the proposed method and compare against some of the state-of-the-art methods.
Bibliographical noteFunding Information:
GVG and FA acknowledge support from the NIHR Birmingham ECMC, NIHR Birmingham SRMRC, Nanocommons H2020-EU (731032 ) and the NIHR Birmingham Biomedical Research Centre and the MRC Heath Data Research UK (HDRUK/CFC/01), an initiative funded by UK Research and Innovation, Department of Health and Social Care (England) and the devolved administrations, and leading medical research charities. The views expressed in this publication are those of the authors and not necessarily those of the NHS, the National Institute for Health Research, the Medical Research Council or the Department of Health.
- Graph characterisation
- Graph entropy
- Information functional
ASJC Scopus subject areas
- Signal Processing
- Computer Vision and Pattern Recognition
- Artificial Intelligence