Clustering-Oriented Generative Attribute Graph Imputation

TL;DR

This paper introduces CGIR, a novel clustering-oriented generative imputation model for attribute-missing graph clustering that improves class-specific attribute imputation and refinement by leveraging subcluster distributions and edge attention mechanisms.

Contribution

The paper proposes CGIR, a unified framework that enhances attribute imputation and embedding refinement for attribute-missing graph clustering through subcluster estimation and edge attribute selection.

Findings

CGIR outperforms state-of-the-art methods in experiments.

It effectively captures class-specific attributes for better clustering.

The model reduces redundant attribute influence during graph refinement.

Abstract

Attribute-missing graph clustering has emerged as a significant unsupervised task, where only attribute vectors of partial nodes are available and the graph structure is intact. The related models generally follow the two-step paradigm of imputation and refinement. However, most imputation approaches fail to capture class-relevant semantic information, leading to sub-optimal imputation for clustering. Moreover, existing refinement strategies optimize the learned embedding through graph reconstruction, while neglecting the fact that some attributes are uncorrelated with the graph. To remedy the problems, we establish the Clustering-oriented Generative Imputation with reliable Refinement (CGIR) model. Concretely, the subcluster distributions are estimated to reveal the class-specific characteristics precisely, and constrain the sampling space of the generative adversarial module, such that the imputation nodes are impelled to align with the correct clusters. Afterwards, multiple subclusters are merged to guide the proposed edge attention network, which identifies the edge-wise attributes for each class, so as to avoid the redundant attributes in graph reconstruction from disturbing the refinement of overall embedding. To sum up, CGIR splits attribute-missing graph clustering into the search and mergence of subclusters, which guides to implement node imputation and refinement within a unified framework. Extensive experiments prove the advantages of CGIR over state-of-the-art competitors.