Reproduce “Bayesian Evidence Accumulation for Graph-Based Learning in Dynamic Data-Driven Applications Systems” 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
Moises Ponce, Sarah Harkins Dayton, Ioannis Schizas, Vasileios Maroulas
B-EAGLe turns graph classification into sequential decisions from partial observations. It processes local neighborhoods, updates a normalized Bayesian belief over classes, and stops when one class crosses a confidence threshold. On CIFAR10-SP, it reports 90.13 ± 2.75% accuracy, versus 77.22 ± 0.381% for GatedGCN+. This unmatched-budget comparison does not isolate Bayesian updating from multi-view aggregation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.