AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

NetDiff: Graph Diffusion with Improved Global Capabilities to Generate and Update Mobile Network Topologies

Félix Marcoccia, Victor Fagoo, Gilles Monzat de Saint Julien, Cédric Adjih, Thomas Watteyne, Paul Mühlethaler

ICML 2026 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 0 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
add domain-related features to the diffusion graph transformer (ablation)DDPM-GT · 16-node graphssaturation (%): 17.6 -> 13.6Improved
add softmax CAM tokens (ablation)DDPM-GT w/ features · 16-node graphssaturation (%): 13.6 -> 12.9Improved
use unsoftmaxed absolute attention (ACAM) instead of softmax CAM (ablation)NetDiff · 16-node graphssaturation (%): 12.9 -> 12.1Improved
use ACAM instead of CAM tokens (ablation)NetDiff · 16-node graphsconnected (%) and parity (%): 98.68 -> 98.68 connected; 98.63 -> 98.64 parityNo clear effect
add CAM tokens (ablation)DDPM-GT · 16-node graphsnode saturation (%): 11.62 -> 7.98Improved
add ACAM tokens (ablation)DDPM-GT · 16-node graphsnode saturation (%): 11.62 -> 7.05Improved
use the added sector, cosine and parity losses instead of standard BCE (ablation)NetDiff (ACAM) · 16-node graphsparity (%): 62.23 -> 98.64Improved
use the added losses instead of standard BCE (ablation)NetDiff (ACAM) · 16-node graphsnode saturation (%): 15.90 -> 7.05Improved
increase ACAM tokens from 1 to 16 (ablation)NetDiff · 16-node graphssaturation metrics: reduces saturation by approximately 0.8%Improved
use NetDiff topologies instead of DDPM-GTNetDiff · 32-node networksthroughput (Mbps): 258.90 -> 322.40Improved
use partial diffusion for reconfiguration instead of full generationNetDiff · 16-node graphs, mobilitysimilarity to previous topology: about 21 % more similarImproved
use noise-less minor reconfiguration with 7 to 10 stepsNetDiff · 16-node graphs, minor movementsimilarity to previous topology: 41 % more similarImproved

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