In this paper, we propose a next-generation link prediction method, Weisfeiler-Lehman
Neural Machine (WLNM), which learns topological features in the form of graph patterns that …

Highlights•Gap-filling is an important tool for making model-driven metabolic
discoveries.•Recent gap-filling algorithms are more efficient and/or show superior …

As a natural extension of link prediction on graphs, hyperlink prediction aims for the
inference of missing hyperlinks in hypergraphs, where a hyperlink can connect more than …

Motivation Metabolic network reconstructions are often incomplete. Constraint-based and
pattern-based methodologies have been used for automated gap filling of these networks …

While graphs capture pairwise relations between entities, hypergraphs deal with higher-
order ones, thereby ensuring losslessness. However, in hyperlink (ie, higher-order link) …

The enclosing subgraph of a target link has been proved to be effective for prediction of
potential links. However, it is still unclear what topological features of the subgraph play the …

Usual networks lossily (if not incorrectly) represent higher-order relations, which calls for
complex structures such as hypergraphs to be used instead. Akin to the link prediction …

Many real-world problems can be modelled in the form of complex networks. Social
networks such as research collaboration networks and facebook, biological neural networks …

Abstract Existing Graph Neural Network (GNN) methods that learn inductive unsupervised
graph representations focus on learning node and edge representations by predicting …

Link prediction tremendously gained concern in the field of machine learning by virtue of its
real-world applicability on various fields including social network analysis, biomedicine, e …