2025/05/26 by Jun Wang, Wang, Juntong, Xiyuan Wang +3
Computer Science · Neuroscience · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Brain Tumor Detection and Classification #Data redundancy #FOS: Computer and information sciences #Leverage (statistics) #Link (geometry) #Machine Learning (cs.LG) #Network Security and Intrusion Detection #Normalization (sociology) #Orthogonalization #Pairwise comparison #Redundancy (engineering)
paper · pdf · doi:10.48550/arxiv.2505.19719
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/05/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Common Neighbors (CNs) and their higher-order variants are important pairwise features widely used in state-of-the-art link prediction methods. However, existing methods often struggle with the repetition across different orders of CNs and fail to fully leverage their potential. We identify that these limitations stem from two key issues: redundancy and over-smoothing in high-order common neighbors. To address these challenges, we design orthogonalization to eliminate redundancy between different-order CNs and normalization to mitigate over-smoothing. By combining these two techniques, we propose Orthogonal Common Neighbor (OCN), a novel approach that significantly outperforms the strongest baselines by an average of 7.7% on popular link prediction benchmarks. A thorough theoretical analysis is provided to support our method. Ablation studies also verify the effectiveness of our orthogonalization and normalization techniques. Code is available at: https://github.com/qingpingmo/OCN.