AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

MIGDiff: Multi-attributes Imputations for Attribute-missing Graphs via Graph Denoising Diffusion Model

Ye Liu, Yang Chen, Hongmin Cai

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 2 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 structural (topological) embeddings (ablation)MIGDiff · Cora (0.4 observed rate)Recall@10 (%): 13.82 -> 17.65Improved
add attribute embeddings (ablation)MIGDiff · Cora (0.4 observed rate)Recall@10 (%): 17.37 -> 17.65Improved
use graph auto-encoder with both embeddings instead of a plain MLP (ablation)MIGDiff · Cora (0.4 observed rate)Recall@10 (%): 10.78 -> 17.65Improved
add VAE-style multi-imputation to VAEVAE baseline · Cora (0.4 observed rate)Recall@10 (%): 8.84 -> 12.44Improved
add VAE-style multi-imputation to SATSAT · Cora (0.4 observed rate)Recall@10 (%): 16.29 -> 12.32Hurt
add VAE-style multi-imputation to ITRITR · Cora (0.4 observed rate)Recall@10 (%): 16.40 -> 15.46Hurt
use diffusion generation instead of VAE-based multi-imputationmulti-attribute imputation · Cora diversity, k=5average variance: 0.0378 -> 2.9455Improved
expand graph with three imputed attribute graphsMIGDiff · node classification, GCN (four datasets)accuracyImproved
use MIGDiff over best single-attribute baseline with MLP classifierMIGDiff · Citeseer node classification, MLPaccuracy (%): 68.91 -> 68.73No clear effect
use MIGDiff at low observed rate (0.2)MIGDiff · Cora, observed rate 0.2Recall/NDCGNo clear effect
increase number of imputation samples k (ablation)MIGDiff · Cora diversityaverage variance: 1.8388 -> 2.9455Improved

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