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

2025-05-26

AI Summary

Existing link prediction methods suffer from redundancy and oversmoothing when modeling multi-order common neighbors, leading to degraded representation capability for higher-order features. To address this, we propose the Orthogonal Common Neighbor (OCN) paradigm: (1) we introduce orthogonalization to eliminate linear redundancy among common neighbors of different orders; (2) we integrate normalization to mitigate oversmoothing; and (3) we formulate a differentiable, interpretable framework for high-order common neighbor modeling. Theoretical analysis reveals that OCN preserves discriminative neighborhood structural information. On mainstream benchmarks, OCN achieves an average improvement of 7.7% over the strongest baseline. Ablation studies comprehensively validate the effectiveness and necessity of each component.

Technology Category

• Machine Learning: Other Foundations of Machine Learning
• Knowledge Representation and Reasoning: Common-Sense Reasoning
• Computer Vision: Other Foundations of Computer Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

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.

Problem

• Addressing redundancy in higher-order common neighbors
• Mitigating over-smoothing in link prediction features
• Improving link prediction accuracy via orthogonalization and normalization

Innovation

• Orthogonalization eliminates redundancy in common neighbors
• Normalization mitigates over-smoothing in high-order neighbors
• OCN combines both techniques for superior link prediction