PLACE: Prompt Learning for Attributed Community Search

TL;DR

PLACE introduces a novel prompt learning framework for attributed community search in large graphs, leveraging prompt-tuning concepts from NLP to improve pattern detection and attribute similarity identification.

Contribution

It pioneers the integration of prompt-tuning into graph neural networks for community search, enhancing scalability and effectiveness on large-scale graphs.

Findings

PLACE outperforms state-of-the-art methods with 22% higher F1 scores.

The framework effectively handles million-scale graphs.

Prompt tokens improve structural and attribute pattern recognition.

Abstract

In this paper, we propose PLACE (Prompt Learning for Attributed Community Search), an innovative graph prompt learning framework for ACS. Enlightened by prompt-tuning in Natural Language Processing (NLP), where learnable prompt tokens are inserted to contextualize NLP queries, PLACE integrates structural and learnable prompt tokens into the graph as a query-dependent refinement mechanism, forming a prompt-augmented graph. Within this prompt-augmented graph structure, the learned prompt tokens serve as a bridge that strengthens connections between graph nodes for the query, enabling the GNN to more effectively identify patterns of structural cohesiveness and attribute similarity related to the specific query. We employ an alternating training paradigm to optimize both the prompt parameters and the GNN jointly. Moreover, we design a divide-and-conquer strategy to enhance scalability, supporting the model to handle million-scale graphs. Extensive experiments on 9 real-world graphs demonstrate the effectiveness of PLACE for three types of ACS queries, where PLACE achieves higher F1 scores by 22% compared to the state-of-the-arts on average.