AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Robust Graph Diffusion Model

Yancheng Wang, Ping Li, Dongfang Sun, Yingzhen Yang

NeurIPS 2026 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a diffusion-based approach to synthesize graph structure (synthetic nodes and their edges) within an existing graph, as stated in the abstract.

Problem

Existing diffusion models for graphs generate whole or small graphs, but no diffusion approach synthesizes graph structures inside an existing graph, including synthetic nodes and their connections.

Approach

Applies diffusion generation to extend an existing graph with synthetic nodes and edges, rather than generating entire graphs from scratch. Only the abstract's framing is available, so finer details are not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
augment training graph with RGDM synthetic structuresGCN · Cora, 25% Metattackaccuracy: 47.5 -> 61.4Improved
augment training graph with RGDM synthetic structuresSG-GSR · Cora, 25% Metattackaccuracy: 77.8 -> 79.1Improved
augment clean graph with RGDMGCN and SG-GSR · clean graphs (4 datasets)accuracy: +0.4 to +2.6 for SG-GSRImproved
add sparsification loss to RGAE (ablation)RGDM (GCN) · Cora, 25% Metattackaccuracy: 56.72 -> 61.42Improved
add low-rank latent regularization (TNN) (ablation)RGDM (GCN) · Cora, 25% Metattackaccuracy: 60.04 -> 61.42Improved
use TNN instead of weight orthogonality or low-rank adjacency regularizers (ablation)RGDM (GCN) · Citeseer, 25% Metattackaccuracy: 61.12 -> 62.84Improved
add edge selection to DoG augmentation (ablation)DoG with SG-GSR · 25% Metattack, Coraaccuracy: 75.6 -> 76.6Improved
add latent TNN (ablation)DoG + edge selection · 25% Metattack, Coraaccuracy: 76.6 -> 77.4Improved
replace BLND decoder with SHED (ablation)RGDM · 25% Metattack, Coraaccuracy: 77.4 -> 79.1Improved
use plain DoG augmentation with SG-GSR (ablation)SG-GSR · 25% Metattack, Coraaccuracy: 77.8 -> 75.6Hurt
use RGDM over DoG and LR-FGDM augmentationGCN · 25% Metattackaccuracy: +2.02 over DoG on CoraImproved
use RGDM on heterophilic graphsLHS · Chameleon, Actor under Metattackaccuracy: 70.03 -> 72.41 (Chameleon 25%)Improved

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