Weisfeiler–Leman algorithm
PulseAugur coverage of Weisfeiler–Leman algorithm — every cluster mentioning Weisfeiler–Leman algorithm across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New research unifies relational and temporal GNN expressivity
Researchers have explored the expressivity of sparse graph neural networks (GNNs) within the framework of the Strong Expressive Lottery Ticket Hypothesis (SELTH). The study generalizes this hypothesis to multi-relationa…
-
Graph Transformers for MILPs Limited by 1-WL Test, Study Finds
A new paper characterizes the expressive power of global-attention graph transformers used for mixed-integer linear programs (MILPs). The research proves that these models, including architectures like Graphormer and Se…
-
New GPU method scales graph neural network expressiveness analysis to massive graphs
Researchers have developed a new method to analyze the expressiveness of graph neural networks (GNNs) by scaling Weisfeiler-Leman (1-WL) stable coloring computations to massive graphs. Their approach utilizes a linear-a…
-
New paper reveals fundamental expressivity limits in MP-GNNs
A new research paper titled "Lost in Aggregation: On a Fundamental Expressivity Limit of Message-Passing Graph Neural Networks" by Eran Rosenbluth explores a theoretical limitation in Message-Passing Graph Neural Networ…
-
New PRiSM method offers complete graph canonicalization for GNNs
Researchers have demonstrated that the Weisfeiler-Leman (WL) test, a common method for graph isomorphism testing, is incomplete for graphs with simple spectra. This limitation extends to Graph Neural Networks (GNNs) tha…