Ordered Subgraph Aggregation Networks

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.

SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks

1 code implementation • 25 Mar 2022 • Christopher Morris, Gaurav Rattan, Sandra Kiefer, Siamak Ravanbakhsh

While (message-passing) graph neural networks have clear limitations in approximating permutation-equivariant functions over graphs or general relational data, more expressive, higher-order graph neural networks do not scale to large graphs.

Weisfeiler--Leman and Graph Spectra

no code implementations • 4 Mar 2021 • Gaurav Rattan, Tim Seppelt

Cospectrality yields an equivalence relation on the family of graphs which is provably weaker than isomorphism.

Data Structures and Algorithms Discrete Mathematics Combinatorics 03B70, 05C81, 05C50, 05C85, 15A18, 15A24, 15A69 (Primary) 68R05, 68R10 (Secondary) F.4; G.2.2

Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings

1 code implementation • NeurIPS 2020 • Christopher Morris, Gaurav Rattan, Petra Mutzel

Hence, it accounts for the higher-order interactions between vertices.

General Classification Graph Classification +1

Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks

1 code implementation • 4 Oct 2018 • Christopher Morris, Martin Ritzert, Matthias Fey, William L. Hamilton, Jan Eric Lenssen, Gaurav Rattan, Martin Grohe

We show that GNNs have the same expressiveness as the $1$-WL in terms of distinguishing non-isomorphic (sub-)graphs.

Graph Classification