NCSAC: Effective Neural Community Search via Attribute-augmented Conductance

2025-11-05

IEEE Transactions on Knowledge and Data Engineering

AI Summary

This paper addresses the challenge of jointly modeling attribute information and structural constraints in attributed community search. We propose an end-to-end neural framework that integrates explicit rule-based constraints with deep learning. Our method comprises three stages: graph optimization preprocessing, conductance-driven initial community generation, and policy-gradient-based iterative refinement. Key contributions include: (1) a novel attribute-enhanced conductance metric that unifies node attribute similarity and structural proximity; and (2) the first incorporation of explicit logical rules into a reinforcement learning policy to enable interpretable, constraint-guided community refinement. Evaluated on six real-world attributed graphs against ten state-of-the-art baselines, our approach achieves 5.3–42.4% improvements in F1-score, demonstrating superior accuracy, robustness to noise and parameter variation, and scalability to large graphs.

Technology Category

• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Identifying locally dense communities closely connected to the user-initiated query node is crucial for a wide range of applications. Existing approaches either solely depend on rule-based constraints or exclusively utilize deep learning technologies to identify target communities. Therefore, an important question is proposed: can deep learning be integrated with rule-based constraints to elevate the quality of community search? In this paper, we affirmatively address this question by introducing a novel approach called Neural Community Search via Attribute-augmented Conductance, abbreviated as NCSAC. Specifically, NCSAC first proposes a novel concept of attribute-augmented conductance, which harmoniously blends the (internal and external) structural proximity and the attribute similarity. Then, NCSAC extracts a coarse candidate community of satisfactory quality using the proposed attribute-augmented conductance. Subsequently, NCSAC frames the community search as a graph optimization task, refining the candidate community through sophisticated reinforcement learning techniques, thereby producing high-quality results. Extensive experiments on six real-world graphs and ten competitors demonstrate the superiority of our solutions in terms of accuracy, efficiency, and scalability. Notably, the proposed solution outperforms state-of-the-art methods, achieving an impressive F1-score improvement ranging from 5.3% to 42.4%. For reproducibility purposes, the source code is available at https://github.com/longlonglin/ncsac.

Problem

• Integrating deep learning with rule-based constraints for community search
• Identifying locally dense communities using structural and attribute similarity
• Refining candidate communities through reinforcement learning optimization

Innovation

• Integrates deep learning with rule-based constraints
• Introduces attribute-augmented conductance for community extraction
• Refines communities using reinforcement learning techniques