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

Subgraph matching is a challenging problem with a wide range of applicationsin database systems, biochemistry, and cognitive science. It involvesdetermining whether a given query graph is present within a larger targetgraph. Traditional graph-matching algorithms provide precise results but facechallenges in large graph instances due to the NP-complete problem, limitingtheir practical applicability. In contrast, recent neural network-basedapproximations offer more scalable solutions, but often lack interpretable nodecorrespondences. To address these limitations, this article presents xNeuSM:Explainable Neural Subgraph Matching which introduces Graph Learnable Multi-hopAttention Networks (GLeMA) that adaptively learns the parameters governing theattention factor decay for each node across hops rather than relying on fixedhyperparameters. We provide a theoretical analysis establishing error boundsfor GLeMA's approximation of multi-hop attention as a function of the number ofhops. Additionally, we prove that learning distinct attention decay factors foreach node leads to a correct approximation of multi-hop attention. Empiricalevaluation on real-world datasets shows that xNeuSM achieves substantialimprovements in prediction accuracy of up to 34% compared to approximatebaselines and, notably, at least a seven-fold faster query time than exactalgorithms. The source code of our implementation is available athttps://github.com/martinakaduc/xNeuSM.

xNeuSM: Explainable Neural Subgraph Matching with Graph Learnable Multi-hop Attention Networks