English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Graph classification is a significant problem in many scientific domains. Itaddresses tasks such as the classification of proteins and chemical compoundsinto categories according to their functions, or chemical and structuralproperties. In a supervised setting, this problem can be framed as learning thestructure, features and relationships between features within a set of labelledgraphs and being able to correctly predict the labels or categories of unseengraphs.  A significant difficulty in this task arises when attempting to applyestablished classification algorithms due to the requirement for fixed sizematrix or tensor representations of the graphs which may vary greatly in theirnumbers of nodes and edges. Building on prior work combining explicit tensorrepresentations with a standard image-based classifier, we propose a model toperform graph classification by extracting fixed size tensorial informationfrom each graph in a given set, and using a Capsule Network to performclassification.  The graphs we consider here are undirected and with categorical features onthe nodes. Using standard benchmarking chemical and protein datasets, wedemonstrate that our graph Capsule Network classification model using anexplicit tensorial representation of the graphs is competitive with currentstate of the art graph kernels and graph neural network models despite onlylimited hyper-parameter searching.

Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations