OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction

Juntong Wang, Xiyuan Wang, Muhan Zhang

Keywords: Link Prediction, Higher-Order Common Neighbors, Structural Features, Probabilistic Modeling, Orthogonality

TL;DR: We design orthogonalization to eliminate redundancy between different-order Common Neighbors and normalization to mitigate over-smoothing for link prediction..

Abstract: 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.

Primary Area: Deep learning (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 6119