Link prediction is a key problem for network-structured data. Link prediction heuristics use
some score functions, such as common neighbors and Katz index, to measure the likelihood …

In many real-world network datasets such as co-authorship, co-citation, email
communication, etc., relationships are complex and go beyond pairwise. Hypergraphs …

Hypergraphs provide an effective abstraction for modeling multi-way group interactions
among nodes, where each hyperedge can connect any number of nodes. Different from …

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

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 …

Deep learning methods for graphs achieve remarkable performance on many node-level
and graph-level prediction tasks. However, despite the proliferation of the methods and their …

Link prediction insimple graphs is a fundamental problem in which new links between
vertices are predicted based on the observed structure of the graph. However, in many real …

Hypergraphs provide a natural representation for many real world datasets. We propose a
novel framework, HNHN, for hypergraph representation learning. HNHN is a hypergraph …

Graph neural networks achieve high accuracy in link prediction by jointly leveraging graph
topology and node attributes. Topology, however, is represented indirectly; state-of-the-art …

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 …