Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Geometrical and Topological Representation Learning

WEISFEILER AND LEMAN GO INFINITE: SPECTRAL AND COMBINATORIAL PRE-COLORINGS

Or Feldman · Amit Boyarski · Shai Feldman · Dani Kogan · Avi Mendelson · Chaim Baskin

Keywords: [ graph neural networks ]


Abstract:

Two popular alternatives for graph isomorphism testing that offer a good trade-off between expressive power and computational efficiency are combinatorial (i.e., obtained via the Weisfeiler-Leman (WL) test) and spectral invariants. While the exact power of the latter is still an open question, the former is regularly criticized for its limited power, when a standard configuration of uniform pre-coloring is used. This drawback hinders the applicability of Message Passing Graph Neural Networks (MPGNNs), whose expressive power is upper bounded by the WL test. Relaxing the assumption of uniform pre-coloring, we show that one can increase the expressive power of the WL test ad infinitum. Following that, we propose an efficient pre-coloring based on spectral features that provably increase the expressive power of the vanilla WL test.The code to reproduce our experiments is available at \url{https://github.com/TPFI22/Spectral-and-Combinatorial}

Chat is not available.