Divide-Then-Rule: A Cluster-Driven Hierarchical Interpolator for Attribute-Missing Graphs

TL;DR

This paper introduces DTRGC, a novel hierarchical method for imputing missing node attributes in graphs, which improves clustering performance by leveraging cluster-aware propagation, hierarchical imputation, and multi-hop representation enhancement.

Contribution

The paper proposes DTRGC, a new divide-then-rule approach that effectively imputes missing attributes in graphs by combining clustering, hierarchical imputation, and multi-hop information integration.

Findings

DTRGC significantly improves clustering accuracy on six graph datasets.

The hierarchical imputation strategy effectively handles nodes with varying neighborhood information.

Cluster-aware propagation enhances the quality of attribute imputation.

Abstract

Deep graph clustering (DGC) for attribute-missing graphs is an unsupervised task aimed at partitioning nodes with incomplete attributes into distinct clusters. Addressing this challenging issue is vital for practical applications. However, research in this area remains underexplored. Existing imputation methods for attribute-missing graphs often fail to account for the varying amounts of information available across node neighborhoods, leading to unreliable results, especially for nodes with insufficient known neighborhood. To address this issue, we propose a novel method named Divide-Then-Rule Graph Completion (DTRGC). This method first addresses nodes with sufficient known neighborhood information and treats the imputed results as new knowledge to iteratively impute more challenging nodes, while leveraging clustering information to correct imputation errors. Specifically, Dynamic Cluster-Aware Feature Propagation (DCFP) initializes missing node attributes by adjusting propagation weights based on the clustering structure. Subsequently, Hierarchical Neighborhood-aware Imputation (HNAI) categorizes attribute-missing nodes into three groups based on the completeness of their neighborhood attributes. The imputation is performed hierarchically, prioritizing the groups with nodes that have the most available neighborhood information. The cluster structure is then used to refine the imputation and correct potential errors. Finally, Hop-wise Representation Enhancement (HRE) integrates information across multiple hops, thereby enriching the expressiveness of node representations. Experimental results on six widely used graph datasets show that DTRGC significantly improves the clustering performance of various DGC methods under attribute-missing graphs.