A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests

02/14/2023
βˆ™
by   Bohang Zhang, et al.
βˆ™
0
βˆ™

Recently, subgraph GNNs have emerged as an important direction for developing expressive graph neural networks (GNNs). While numerous architectures have been proposed, so far there is still a limited understanding of how various design paradigms differ in terms of expressive power, nor is it clear what design principle achieves maximal expressiveness with minimal architectural complexity. To address these fundamental questions, this paper conducts a systematic study of general node-based subgraph GNNs through the lens of Subgraph Weisfeiler-Lehman Tests (SWL). Our central result is to build a complete hierarchy of SWL with strictly growing expressivity. Concretely, we prove that any node-based subgraph GNN falls into one of the six SWL equivalence classes, among which 𝖲𝖲𝖢𝖫 achieves the maximal expressive power. We also study how these equivalence classes differ in terms of their practical expressiveness such as encoding graph distance and biconnectivity. Furthermore, we give a tight expressivity upper bound of all SWL algorithms by establishing a close relation with localized versions of WL and Folklore WL (FWL) tests. Our results provide insights into the power of existing subgraph GNNs, guide the design of new architectures, and point out their limitations by revealing an inherent gap with the 2-FWL test. Finally, experiments demonstrate that 𝖲𝖲𝖢𝖫-inspired subgraph GNNs can significantly outperform prior architectures on multiple benchmarks despite great simplicity.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
βˆ™ 06/22/2022

Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries

Subgraph GNNs are a recent class of expressive Graph Neural Networks (GN...
research
βˆ™ 03/22/2022

Twin Weisfeiler-Lehman: High Expressive GNNs for Graph Classification

The expressive power of message passing GNNs is upper-bounded by Weisfei...
research
βˆ™ 06/22/2022

Ordered Subgraph Aggregation Networks

Numerous subgraph-enhanced graph neural networks (GNNs) have emerged rec...
research
βˆ™ 05/08/2023

From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks

Relational pooling is a framework for building more expressive and permu...
research
βˆ™ 08/16/2023

The Expressive Power of Graph Neural Networks: A Survey

Graph neural networks (GNNs) are effective machine learning models for m...
research
βˆ™ 01/23/2023

Rethinking the Expressive Power of GNNs via Graph Biconnectivity

Designing expressive Graph Neural Networks (GNNs) is a central topic in ...
research
βˆ™ 01/26/2023

WL meet VC

Recently, many works studied the expressive power of graph neural networ...

Please sign up or login with your details

Forgot password? Click here to reset