Pre-trained Prompt-driven Semi-supervised Local Community Detection

TL;DR

This paper introduces PPSL, a novel semi-supervised local community detection method using pre-trained prompts, which improves both accuracy and efficiency over existing approaches.

Contribution

The paper proposes PPSL, a new framework combining graph neural networks and prompt-driven fine-tuning for faster, more accurate community detection.

Findings

PPSL outperforms baseline methods in community quality.

PPSL demonstrates higher efficiency in community detection tasks.

Experimental results on five datasets validate PPSL's effectiveness.

Abstract

Semi-supervised local community detection aims to leverage known communities to detect the community containing a given node. Although existing semi-supervised local community detection studies yield promising results, they suffer from time-consuming issues, highlighting the need for more efficient algorithms. Therefore, we apply the "pre-train, prompt" paradigm to semi-supervised local community detection and propose the Pre-trained Prompt-driven Semi-supervised Local community detection method (PPSL). PPSL consists of three main components: node encoding, sample generation, and prompt-driven fine-tuning. Specifically, the node encoding component employs graph neural networks to learn the representations of nodes and communities. Based on representations of nodes and communities, the sample generation component selects known communities that are structurally similar to the local structure of the given node as training samples. Finally, the prompt-driven fine-tuning component leverages these training samples as prompts to guide the final community prediction. Experimental results on five real-world datasets demonstrate that PPSL outperforms baselines in both community quality and efficiency.