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

2024-10-29

AI Summary

To address low clustering accuracy, training instability, and poor scalability caused by noisy edges in real-world graph data, this paper proposes a robust graph clustering framework. The core innovation is a dual soft-assignment协同 mechanism: (i) global soft assignment based on topology-attribute fused embeddings and a structural affinity matrix; and (ii) node-level local soft assignment guided by explicitly modeled community landmarks. This paradigm jointly optimizes global graph structure while ensuring robust local reassignment under noise. Integrating deep graph neural networks (GNNs), self-supervised joint optimization, and landmark-driven guidance, the method achieves significant improvements over state-of-the-art approaches across multiple real-world graph benchmarks—demonstrating higher clustering accuracy, enhanced noise resilience, improved training stability, and efficient scalability to graphs with thousands of nodes.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

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.

Problem

• Graph Clustering
• Deep Learning
• Noisy Edges

Innovation

• Dual Soft Assignment
• Robust Deep Graph Clustering
• Noise Resistance