AI Paper Atlas

Research map / Graph learning / GNN architectures

Metadata-conscious anonymous messaging

ICML 2016 · Graph learning › GNN architectures · approach: Graph rewiring and scalable message passing · 6 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use adaptive diffusion (tree protocol) instead of standard diffusionmessage spreading on d-regular trees vs spy-based adversary · d-regular trees, spy-based adversaryprobability of detectionHelped
Use adaptive diffusion instead of standard diffusion on the Facebook graphmessage spreading on real social graph · Facebook dataset, spy probability p≤0.15probability of detectionHelped
Increase tree degree d under standard diffusionstandard diffusion on d-regular trees · d-regular trees, spy-based adversaryprobability of detectionHurt
Increase tree degree d under adaptive diffusionadaptive diffusion on d-regular trees · d-regular trees, spy-based adversaryprobability of detectionHelped
Add snapshot observations to spy adversary (spy+snapshot) (ablation)adaptive diffusion · regular trees, spy+snapshot adversaryprobability of detectionNo clear effect

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