Graph Clustering with Cross-View Feature Propagation

TL;DR

This paper introduces GCCFP, a novel graph clustering method that uses multi-view feature propagation to improve cluster detection, demonstrating superior performance on real-world graphs.

Contribution

GCCFP is the first method to leverage cross-view feature propagation with a unified objective for enhanced graph clustering.

Findings

GCCFP outperforms existing clustering methods on multiple real-world datasets.

The proposed algorithm converges within a finite number of iterations.

GCCFP effectively combines topology and multi-view features for better clustering results.

Abstract

Graph clustering is a fundamental and challenging learning task, which is conventionally approached by grouping similar vertices based on edge structure and feature similarity.In contrast to previous methods, in this paper, we investigate how multi-view feature propagation can influence cluster discovery in graph data.To this end, we present Graph Clustering With Cross-View Feature Propagation (GCCFP), a novel method that leverages multi-view feature propagation to enhance cluster identification in graph data.GCCFP employs a unified objective function that utilizes graph topology and multi-view vertex features to determine vertex cluster membership, regularized by a module that supports key latent feature propagation. We derive an iterative algorithm to optimize this function, prove model convergence within a finite number of iterations, and analyze its computational complexity. Our experiments on various real-world graphs demonstrate the superior clustering performance of GCCFP compared to well-established methods, manifesting its effectiveness across different scenarios.