no code implementations • 12 Feb 2024 • Billy J. Franks, Christopher Morris, Ameya Velingker, Floris Geerts
Moreover, we focus on augmenting $1$-WL and MPNNs with subgraph information and employ classical margin theory to investigate the conditions under which an architecture's increased expressivity aligns with improved generalization performance.
no code implementations • 6 Oct 2023 • Pablo Barceló, Tamara Cucumides, Floris Geerts, Juan Reutter, Miguel Romero
The problem of answering logical queries over incomplete knowledge graphs is receiving significant attention in the machine learning community.
1 code implementation • 26 Jan 2023 • Christopher Morris, Floris Geerts, Jan Tönshoff, Martin Grohe
Secondly, when an upper bound on the graphs' order is known, we show a tight connection between the number of graphs distinguishable by the $1\text{-}\mathsf{WL}$ and GNNs' VC dimension.
no code implementations • 22 Jun 2022 • Chendi Qian, Gaurav Rattan, Floris Geerts, Christopher Morris, Mathias Niepert
Numerous subgraph-enhanced graph neural networks (GNNs) have emerged recently, provably boosting the expressive power of standard (message-passing) GNNs.
no code implementations • ICLR 2022 • Floris Geerts, Juan L. Reutter
We provide an elegant way to easily obtain bounds on the separation power of GNNs in terms of the Weisfeiler-Leman (WL) tests, which have become the yardstick to measure the separation power of GNNs.
no code implementations • 17 Mar 2022 • Floris Geerts, Jasper Steegmans, Jan Van den Bussche
We investigate the power of message-passing neural networks (MPNNs) in their capacity to transform the numerical features stored in the nodes of their input graphs.
1 code implementation • NeurIPS 2021 • Pablo Barceló, Floris Geerts, Juan Reutter, Maksimilian Ryschkov
We propose local graph parameter enabled GNNs as a framework for studying the latter kind of approaches and precisely characterize their distinguishing power, in terms of a variant of the WL test, and in terms of the graph structural properties that they can take into account.
no code implementations • 23 Jul 2020 • Floris Geerts
The expressive power of graph neural network formalisms is commonly measured by their ability to distinguish graphs.
no code implementations • 16 Jun 2020 • Floris Geerts
When it comes to concrete learnable graph neural network (GNN) formalisms that match 2-WL or W[$\ell$] in expressive power, we consider second-order graph neural networks that allow for non-linear layers.
no code implementations • 6 Apr 2020 • Floris Geerts, Filip Mazowiecki, Guillermo A. Pérez
In this paper we cast neural networks defined on graphs as message-passing neural networks (MPNNs) in order to study the distinguishing power of different classes of such models.