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

Ye Liu; Yang Chen; Hongmin Cai

AAAI 2026technical0 citations

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

Abstract

The missing of graph attributes poses a significant challenge in graph representation learning. Some existing graph attribute completion methods adopt the shared-space hypothesis or employ end-to-end frameworks to perform single-attribute imputation. However, these models can only generate one single attribute with a few specific patterns that either adhere to prior knowledge or are optimal for downstream tasks, making it difficult to capture the full range of variations in the target attribute distribution. This limitation negatively impacts the model

BibTeX

@inproceedings{aaai2026_migdiffmultiattr,
  title = {MIGDiff: Multi-attributes Imputations for Attribute-missing Graphs via Graph Denoising Diffusion Model},
  author = {Ye Liu and Yang Chen and Hongmin Cai},
  booktitle = {AAAI 2026},
  year = {2026}
}