Reproduce “Weighted Embeddings for Low-Dimensional Graph Representation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Thomas Bläsius, Jean-Pierre von der Heydt, Maximilian Katzmann, Nikolai Maas
WEMBED represents each graph node with a Euclidean position and a positive weight, using both to measure pairwise distance. The authors optimize positions while fixing degree-based weights, then evaluate edge reconstruction across real and generated graphs. On 2,173 real networks, 8-dimensional WEMBED achieves F1 very close to 1 on over 75%; large-graph scores use sampled non-edges.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.