Researchers have introduced PLACE, a novel graph prompt learning framework designed for attributed community search in large graphs. Inspired by NLP prompt-tuning, PLACE integrates structural and learnable prompt tokens to refine graph queries, enhancing the Graph Neural Network's ability to identify relevant patterns. The framework employs an alternating training paradigm for joint optimization and a divide-and-conquer strategy for scalability on million-node graphs. Experiments show PLACE significantly outperforms state-of-the-art methods, achieving an average F1 score improvement of 22% across various attributed community search tasks. AI
Summary written by gemini-2.5-flash-lite from 1 sources. How we write summaries →
IMPACT Introduces a novel method for attributed community search in large graphs, potentially improving pattern recognition and scalability in graph-based AI applications.
RANK_REASON The cluster contains an academic paper detailing a new method for graph analysis. [lever_c_demoted from research: ic=1 ai=1.0]