Skip to content (access key 's')
Logo of Technion
Logo of CS Department


Improving Graph Neural Networks Expressivity Via Spectral and Combinatorial Pre-Colorings
event speaker icon
Or Feldman, M.Sc. Thesis Seminar
event date icon
Tuesday, 1.3.2022, 11:00
event location icon
Zoom Lecture: 96864188946
event speaker icon
Advisor:  Prof. A. Mendlson
Graph isomorphism testing is usually approached via the comparison of graph invariants. Two popular alternatives 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 increases the expressive power of the vanilla WL test.
[Back to the index of events]