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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Code classification is a difficult issue in program understanding andautomatic coding. Due to the elusive syntax and complicated semantics inprograms, most existing studies use techniques based on abstract syntax tree(AST) and graph neural network (GNN) to create code representations for codeclassification. These techniques utilize the structure and semantic informationof the code, but they only take into account pairwise associations and neglectthe high-order correlations that already exist between nodes in the AST, whichmay result in the loss of code structural information. On the other hand, whilea general hypergraph can encode high-order data correlations, it is homogeneousand undirected which will result in a lack of semantic and structuralinformation such as node types, edge types, and directions between child nodesand parent nodes when modeling AST. In this study, we propose to represent ASTas a heterogeneous directed hypergraph (HDHG) and process the graph byheterogeneous directed hypergraph neural network (HDHGN) for codeclassification. Our method improves code understanding and can representhigh-order data correlations beyond paired interactions. We assessheterogeneous directed hypergraph neural network (HDHGN) on public datasets ofPython and Java programs. Our method outperforms previous AST-based andGNN-based methods, which demonstrates the capability of our model.

Heterogeneous Directed Hypergraph Neural Network over abstract syntax tree (AST) for Code Classification