Reproduce “Attributed Hypergraph Generation with Realistic Interplay Between Structure and Attributes” 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
Jaewan Chun, Seokbum Yoon, Minyoung Choe, Geon Lee, Kijung Shin
NoAH generates synthetic hypergraph groups by selecting core nodes and then attaching fringe nodes using attribute-conditioned probabilities; NoAHFit learns seed probabilities and affinity matrices from an observed hypergraph. Across nine datasets and six structure–attribute metrics, it achieves average rank 1.5 versus 3.8 for the tied next-best baselines. Experiments use binary attributes, with weaker results on two datasets and HOHE.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.