UniCom: Towards a Unified and Cohesiveness-aware Framework for Community Search and Detection
Yifan Zhu, Hanchen Wang, Wenjie Zhang, Alexander Zhou, Ying Zhang

TL;DR
UniCom introduces a unified, knowledge transfer-based framework for community search and detection that adapts to new graphs without retraining, outperforming existing methods especially with limited supervision.
Contribution
The paper presents UniCom, a novel framework that unifies community search and detection via transfer learning and a lightweight prompt-based approach, enhancing generalization and efficiency.
Findings
Outperforms all baselines across 16 datasets and 22 methods.
Effective with scarce or no supervision.
Maintains runtime efficiency while improving accuracy.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Graph Neural Networks · Complex Network Analysis Techniques · Mobile Crowdsensing and Crowdsourcing
