PLACE: Prompt Learning for Attributed Community Search

2025-07-07

AI Summary

This paper addresses the Attribute Community Search (ACS) problem—discovering cohesive subgraphs that simultaneously satisfy structural cohesiveness and attribute similarity. We introduce prompt learning to ACS for the first time, proposing PromptACS: a novel framework that designs query-dependent structured prompt tokens to dynamically enhance graph connectivity among relevant nodes, and employs alternating training with a divide-and-conquer strategy for efficient, scalable graph neural network optimization. Extensive experiments across nine real-world datasets and three query types demonstrate an average 22% improvement in F1-score over state-of-the-art methods. Our key contributions are: (1) the first application of prompt learning to ACS; (2) a learnable, query-aware graph structure enhancement mechanism; and (3) a solution that jointly achieves high accuracy, computational efficiency, and scalability.

Technology Category

• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Proposes PLACE for attributed community search using prompt learning
• Integrates structural and learnable prompts to refine graph queries
• Enhances GNN performance for structural and attribute similarity patterns

Innovation

• Graph prompt learning framework for ACS
• Alternating training optimizes prompt and GNN
• Divide-and-conquer strategy enhances scalability