Reproduce “Gated Graph Neural Networks for Learning Hidden Independent Cascade Dynamics” 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
Anubha Goel, Illia Oleksiienko, Mateusz Wilinski, Alexandros Iosifidis, Juho Kanniainen
SAGE-HC estimates node-level spreading probabilities from repeated noisy symptoms in hidden independent-cascade processes. It aggregates symptom and graph summaries, then uses a gated graph neural network to modulate neighbor messages. On simulated noisy tests, it outperforms DMP on three Barabási–Albert graphs and Karate Club, but the balanced-tree exception shows results depend on topology.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.