Signals 4 · free daily AI digest

Edge-Girth as a Structural Edge Feature for Graph Neural Networks

Paper recorded by Signals 4 on 2026-09-01 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-01 on arXiv · recorded by Signals 4 on 2026-09-02

Category: cs.LG · 机器学习 · first seen 2026-09-02

Abstract

Graph neural networks (GNN) based on message passing are provably no more powerful than the one-dimensional Weisfeiler--Leman colour-refinement test (1-WL): two graphs it cannot tell apart receive identical representations, however deep or wide the network. A common remedy augments node or edge features with precomputed structural descriptors, most often counts of a fixed small subgraph such as tr

Read on arXiv →

#166 most recent of 215 cs.LG papers we have recorded · ↑ newer: Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoni · ↓ older: Efficiently Estimating Optimal Hyperparameter Scaling Laws through Pow
Cite this page: Edge-Girth as a Structural Edge Feature for Graph Neural Networks: the #166 most recent of 215 cs.LG papers we have recorded (as of 2026-09-01). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/edge-girth-as-a-structural-edge-feature-for-graph-neural-networks.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions