Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering

2025-10-03

AI Summary

Existing contrastive attributed graph clustering (CAGC) methods solely leverage edge-level structural information to enhance node embeddings, neglecting explicit edge embedding modeling and node–edge cross-granularity collaborative enhancement; moreover, they treat all positive and negative sample pairs uniformly without distinguishing hard from easy instances, limiting discriminative capability. To address these limitations, we propose Node–Edge Collaborative Contrastive Learning (NECCL), a novel framework featuring: (i) a hybrid collaborative augmentation mechanism that jointly optimizes node- and edge-level embeddings while modeling their fine-grained interactions; and (ii) a pseudo-label-guided adaptive discrepancy-aware strategy that dynamically reweights contrastive pairs based on instance difficulty. By establishing a multi-level similarity measurement scheme, NECCL achieves significant performance gains over state-of-the-art methods across six benchmark datasets, demonstrating superior robustness and effectiveness.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Multiagent Systems: Adversarial Agents

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
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Due to its powerful capability of self-supervised representation learning and clustering, contrastive attributed graph clustering (CAGC) has achieved great success, which mainly depends on effective data augmentation and contrastive objective setting. However, most CAGC methods utilize edges as auxiliary information to obtain node-level embedding representation and only focus on node-level embedding augmentation. This approach overlooks edge-level embedding augmentation and the interactions between node-level and edge-level embedding augmentations across various granularity. Moreover, they often treat all contrastive sample pairs equally, neglecting the significant differences between hard and easy positive-negative sample pairs, which ultimately limits their discriminative capability. To tackle these issues, a novel robust attributed graph clustering (RAGC), incorporating hybrid-collaborative augmentation (HCA) and contrastive sample adaptive-differential awareness (CSADA), is proposed. First, node-level and edge-level embedding representations and augmentations are simultaneously executed to establish a more comprehensive similarity measurement criterion for subsequent contrastive learning. In turn, the discriminative similarity further consciously guides edge augmentation. Second, by leveraging pseudo-label information with high confidence, a CSADA strategy is elaborately designed, which adaptively identifies all contrastive sample pairs and differentially treats them by an innovative weight modulation function. The HCA and CSADA modules mutually reinforce each other in a beneficent cycle, thereby enhancing discriminability in representation learning. Comprehensive graph clustering evaluations over six benchmark datasets demonstrate the effectiveness of the proposed RAGC against several state-of-the-art CAGC methods.

Problem

• Enhancing node and edge embedding augmentations for graph clustering
• Addressing differential treatment of contrastive sample pairs
• Improving discriminative capability in representation learning

Innovation

• Hybrid node-edge embedding augmentation for similarity measurement
• Adaptive contrastive sample identification using pseudo-labels
• Differential treatment of sample pairs via weight modulation