AI Paper Atlas

Research map / Graph learning / GNN architectures

Let’s Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework

Floris Geerts, Filip Mazowiecki, Guillermo Perez

ICML 2021 · Graph learning › GNN architectures · approach: Subgraph and distance-aware GNNs · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
allow message functions to use vertex degreesMPNNs · labelled graphsdistinguishing power: one step aheadImproved
restrict message functions to depend only on vertex labels, not degreesanonymous MPNNs · labelled graphsdistinguishing powerNo clear effect
use a plain Kipf-Welling GCN instead of WL refinementKipf-Welling GCN · labelled graphsdistinguishing powerHurt
add a learnable trade-off parameter between a vertex's own features and its neighbours' featuresGCNs · labelled graphsdistinguishing powerImproved
use ReLU GNNs with a learnable self-feature trade-off parameterGNNs · fixed input graphWL simulation rounds: one layer in each stepImproved
use dGNN_1 or dGNN_3 rather than a general degree-aware MPNNdGNN_1 and dGNN_3 · labelled graphsdistinguishing powerHurt
use dGNN_2, dGNN_4, dGNN_5, or dGNN_6dGNN architectures · labelled graphsdistinguishing powerMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy