UniCom: Towards a Unified and Cohesiveness-aware Framework for Community Search and Detection

2025-12-02

AI Summary

Existing community search and detection methods suffer from fragmented modeling and reliance on task-specific retraining, resulting in poor generalizability and sharp performance degradation under low-supervision settings. To address this, we propose UniCD—the first unified framework enabling joint modeling of both tasks in unsupervised or extremely low-supervision regimes. UniCD integrates a domain-aware specialization mechanism with a generic graph learning backbone, incorporating prompt-driven lightweight adaptation, multi-source domain pretraining, topology-semantic knowledge distillation, and local structural awareness in representation learning. Additionally, it introduces consistency-aware modeling to enhance cross-graph adaptability. Evaluated on 16 benchmark datasets, UniCD significantly outperforms 22 state-of-the-art baselines—especially in fully unsupervised scenarios—while maintaining model compactness and computational efficiency.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs 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: Vertical and domain-specific search

Abstract

Searching and detecting communities in real-world graphs underpins a wide range of applications. Despite the success achieved, current learning-based solutions regard community search, i.e., locating the best community for a given query, and community detection, i.e., partitioning the whole graph, as separate problems, necessitating task- and dataset-specific retraining. Such a strategy limits the applicability and generalization ability of the existing models. Additionally, these methods rely heavily on information from the target dataset, leading to suboptimal performance when supervision is limited or unavailable. To mitigate this limitation, we propose UniCom, a unified framework to solve both community search and detection tasks through knowledge transfer across multiple domains, thus alleviating the limitations of single-dataset learning. UniCom centers on a Domain-aware Specialization (DAS) procedure that adapts on the fly to unseen graphs or tasks, eliminating costly retraining while maintaining framework compactness with a lightweight prompt-based paradigm. This is empowered by a Universal Graph Learning (UGL) backbone, which distills transferable semantic and topological knowledge from multiple source domains via comprehensive pre-training. Both DAS and UGL are informed by local neighborhood signals and cohesive subgraph structures, providing consistent guidance throughout the framework. Extensive experiments on both tasks across 16 benchmark datasets and 22 baselines have been conducted to ensure a comprehensive and fair evaluation. UniCom consistently outperforms all state-of-the-art baselines across all tasks under settings with scarce or no supervision, while maintaining runtime efficiency.

Problem

• Unifies community search and detection tasks
• Transfers knowledge across domains to reduce retraining
• Improves performance with limited or no supervision

Innovation

• Unified framework for community search and detection
• Domain-aware Specialization adapts without retraining
• Universal Graph Learning backbone transfers knowledge across domains