cs.NE · 2026-11-10 · No. 169
Neural and Evolutionary Computing, 2026-11-10.
1 new papers in cs.NE. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
1 entries-
01
Pricing Symbolic Rules by What GNNs Leave Unlearned
Satabarto Sarkar, Prithwineel Paul
cs.NE · cs.AI · cs.LG
Symbolic knowledge (motif counts, ring counts, label constraints) is routinely added to graph neural networks (GNNs) and justified by their limited expressivity. We replace this yardstick with an exact one. The largest log-loss reduction a rule $S$ can give a model family is $I(Y;S\midσ)$ given what the family computes; every realised gain splits exactly into this term plus repaid neural debt; and for a trained network with representation $T$...
This edition is part of The Daily Abstract — cs.NE archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.