Skip to content
Back to skills

Speqnets Sparsityaware Permutationequivariant Graph Networks

ASecurity

**arXiv ID:** 2203.13913 **Authors:** Christopher Morris, Gaurav Rattan, Sandra Kiefer, Siamak Ravanbakhsh **Published:** 2022-03-25T21:17:09Z **Abstract:** 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. They either operate on $k$-order tensors or consider all $k$-node subgraphs, implying an exponenti...

  • 3 stars
  • 0 votes
  • 0 copies
  • 6 views
  • Added September 11, 2026
toolsnodeexpressperformance

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill speqnets-sparsityaware-permutationequivariant-graph-networks --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Speqnets Sparsityaware Permutationequivariant Graph Networks?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Speqnets Sparsityaware Permutationequivariant Graph Networks
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-speqnets-sparsityaware-permutationequivariant-grap/badge)](https://www.skillsdirectory.com/skills/hiyenwong-speqnets-sparsityaware-permutationequivariant-grap)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks

**arXiv ID:** 2203.13913
**Authors:** Christopher Morris, Gaurav Rattan, Sandra Kiefer, Siamak Ravanbakhsh
**Published:** 2022-03-25T21:17:09Z
**Abstract:**
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. They either operate on $k$-order tensors or consider all $k$-node subgraphs, implying an exponential dependence on $k$ in memory requirements, and do not adapt to the sparsity of the graph. By introducing new heuristics for the graph isomorphism problem, we devise a class of universal, permutation-equivariant graph networks, which, unlike previous architectures, offer a fine-grained control between expressivity and scalability and adapt to the sparsity of the graph. These architectures lead to vastly reduced computation times compared to standard higher-order graph networks in the supervised node- and graph-level classification and regression regime while significantly improving over standard graph neural network and graph kernel architectures in terms of predictive performance.

## Skill Description

This skill is generated from the arXiv paper: SpeqNets: Sparsity-aware Permutation-equivariant Graph Networks (2203.13913).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2203.13913](http://arxiv.org/abs/2203.13913v3)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.