mlsanityData to 14 Oct 2026

The Boolean Power of ReLU

arXiv 2608.12617 ↗First posted 12 Aug 2026cs.LG cs.LOcited by 0

Not on the map. Why?

Abstract (arXiv)

We prove that, on finite simple undirected graphs equipped with a single Boolean node feature, the Boolean queries expressible in Sigma-MPLang, for any collection Sigma of eventually constant activation functions and with arbitrary real coefficients, form a strict subclass of the Boolean queries expressible in ReLU-MPLang. We thereby settle a recently posed open problem: whether ReLU-MPLang is more powerful than trReLU-MPLang when it comes to Boolean queries. In particular, this implies that ReLU-GNNs are strictly more expressive than TrReLU,id-GNNs with respect to Boolean queries on Boolean-featured graphs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 4 of its 4 references that are in the map. First posted on arXiv 12 Aug 2026.

Builds on

4 of 4 references.

References · 4

  1. 2024Decidability of Graph Neural Networks via Logical Characterizationscited by 14
  2. 2022On the expressive power of message-passing neural networks as global feature map transformerscited by 8
  3. 2013Dimension Reduction via Colour Refinementcited by 6
  4. 2025A Logical View of GNN-Style Computation and the Role of Activation Functionscited by 3

Built on by

Not cited yet.