# ProCom: A Few-shot Targeted Community Detection Algorithm

arXiv: https://arxiv.org/abs/2408.07369 · HTML: https://mlsanity.com/paper/2408.07369/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2024.

## Built on by (most cited first, 4 of 4)

- [A Survey of Cross-domain Graph Learning: Progress and Future Directions](https://mlsanity.com/paper/2503.11086/) (2025)
- [Efficient Identity and Position Graph Embedding via Spectral-Based Random Feature Aggregation](https://mlsanity.com/paper/2505.20992/) (2025)
- [Pre-trained Prompt-driven Semi-supervised Local Community Detection](https://mlsanity.com/paper/2505.12304/) (2025)
- [Interpretable Unsupervised Community Detection with LLM-Symbolized Structured Processes](https://mlsanity.com/paper/2608.06402/) (2026)

## Abstract (arXiv)

Targeted community detection aims to distinguish a particular type of community in the network. This is an important task with a lot of real-world applications, e.g., identifying fraud groups in transaction networks. Traditional community detection methods fail to capture the specific features of the targeted community and detect all types of communities indiscriminately. Semi-supervised community detection algorithms, emerged as a feasible alternative, are inherently constrained by their limited adaptability and substantial reliance on a large amount of labeled data, which demands extensive domain knowledge and manual effort. In this paper, we address the aforementioned weaknesses in targeted community detection by focusing on few-shot scenarios. We propose ProCom, a novel framework that extends the ``pre-train, prompt'' paradigm, offering a low-resource, high-efficiency, and transferable solution. Within the framework, we devise a dual-level context-aware pre-training method that fosters a deep understanding of latent communities in the network, establishing a rich knowledge foundation for downstream task. In the prompt learning stage, we reformulate the targeted community detection task into pre-training objectives, allowing the extraction of specific knowledge relevant to the targeted community to facilitate effective and efficient inference. By leveraging both the general community knowledge acquired during pre-training and the specific insights gained from the prompt communities, ProCom exhibits remarkable adaptability across different datasets. We conduct extensive experiments on five benchmarks to evaluate the ProCom framework, demonstrating its SOTA performance under few-shot scenarios, strong efficiency, and transferability across diverse datasets.