RDSA: A Robust Deep Graph Clustering Framework via Dual Soft Assignment

TL;DR

RDSA is a novel deep graph clustering framework that enhances robustness and scalability by integrating dual soft assignment modules, effectively handling noisy real-world graphs and outperforming existing methods.

Contribution

The paper introduces RDSA, a new deep graph clustering framework with dual soft assignment modules that improve robustness, scalability, and performance on noisy datasets.

Findings

RDSA outperforms state-of-the-art methods on various real-world datasets.

RDSA demonstrates high robustness to noisy edges in graph data.

The framework scales effectively to large datasets.

Abstract

Graph clustering is an essential aspect of network analysis that involves grouping nodes into separate clusters. Recent developments in deep learning have resulted in graph clustering, which has proven effective in many applications. Nonetheless, these methods often encounter difficulties when dealing with real-world graphs, particularly in the presence of noisy edges. Additionally, many denoising graph clustering methods tend to suffer from lower performance, training instability, and challenges in scaling to large datasets compared to non-denoised models. To tackle these issues, we introduce a new framework called the Robust Deep Graph Clustering Framework via Dual Soft Assignment (RDSA). RDSA consists of three key components: (i) a node embedding module that effectively integrates the graph's topological features and node attributes; (ii) a structure-based soft assignment module that improves graph modularity by utilizing an affinity matrix for node assignments; and (iii) a node-based soft assignment module that identifies community landmarks and refines node assignments to enhance the model's robustness. We assess RDSA on various real-world datasets, demonstrating its superior performance relative to existing state-of-the-art methods. Our findings indicate that RDSA provides robust clustering across different graph types, excelling in clustering effectiveness and robustness, including adaptability to noise, stability, and scalability.