דלג לתוכן (מקש קיצור 's')
אירועים

אירועים והרצאות בפקולטה למדעי המחשב ע"ש הנרי ומרילין טאוב

שיפור יכולת הביטוי של רשתות נוירונים גרפיות באמצעות צביעות מקדימות ספקטרליות וקומבינטוריות
event speaker icon
אור פלדמן (הרצאה סמינריונית למגיסטר)
event date icon
יום שלישי, 01.03.2022, 11:00
event location icon
Zoom Lecture: 96864188946
event speaker icon
מנחה: 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.