Weisfeiler-Lehman test
PulseAugur coverage of Weisfeiler-Lehman test — every cluster mentioning Weisfeiler-Lehman test across labs, papers, and developer communities, ranked by signal.
-
New GSWL test incorporates geometry into simplicial message passing models
Researchers have developed a new framework called the Geometric Simplicial Weisfeiler--Lehman (GSWL) test to address limitations in existing message passing networks. The GSWL test enhances the Weisfeiler--Lehman (WL) a…
-
Full-Spectrum GNN advances spectral filtering for expressive and scalable graph learning
Researchers have introduced the Full-Spectrum Graph Neural Network (FSpecGNN), a novel approach that enhances the expressive power of spectral graph neural networks. FSpecGNN generalizes classical spectral GNNs by opera…
-
New research benchmarks and methods advance Graph Neural Network evaluation and design
Several recent arXiv papers explore advancements and challenges in Graph Neural Networks (GNNs). Research includes methods for verifying GNN ownership and detecting copycat models, as well as developing unified benchmar…