Link prediction on multi-relational graphs from an influence propagation perspective

2026/08/05 by Zidu Yin, Yuankai Qi, Dong Gong +3
Computer Science · #cs.SI #cs.LG

paper · pdf · doi:10.1016/j.patcog.2026.114039

published as Pattern Recognition 180 (2026) 114039 · Accepted for publication in Pattern Recognition

arxiv created 2026/08/05 · arxiv updated 2026/08/06

Abstract

Predicting the existence and type of links (edges) between nodes in a multi-relational graph is key for applications from social interaction prediction to knowledge relationship identification. Enhancing local features with relevant global information is crucial for accurate link prediction, yet it remains challenging. We address this by modeling the relationship between node pairs as node influence. That is, whether the node influence can be propagated and what type of influence is propagated indicates where and what type the edge is, which will be the most relevant local and global information to predict the edges. To this end, we extend the Susceptible-Infectious-Recovered (SIR) epidemic model to capture the influence propagation of nodes on a large scale through sub-graph structures. Subsequently, these sub-graphs are compressed using virtual edges, thereby substantially reducing the computation associated with utilizing the global graph structure. Finally, we propose the Influential Graph Neural Predictor, referred to as IGNP, a link prediction framework guided by influence propagation. Extensive experiments demonstrate the superiority of the proposed method, which outperforms strong baselines by a large margin on the widely used and real-world datasets.

Citations

• Reconsidering the Performance of GAE in Link Prediction
• PageRank Bandits for Link Prediction
• Motif-aware Riemannian Graph Neural Network with Generative-Contrastive Learning
• Local Structure-aware Graph Contrastive Representation Learning
• Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking
• Neural Common Neighbor with Completion for Link Prediction
• Graph Neural Networks for Link Prediction with Subgraph Sketching
• Graph Contrastive Learning with Adaptive Augmentation
• Data Augmentation for Graph Neural Networks
• Heterogeneous Graph Transformer
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Relational inductive biases, deep learning, and graph networks
• Link Prediction Based on Graph Neural Networks
• Graph Partition Neural Networks for Semi-Supervised Classification
• GeniePath: Graph Neural Networks with Adaptive Receptive Paths
• HARP: Hierarchical Representation Learning for Networks
• Inductive Representation Learning on Large Graphs
• struc2vec: Learning Node Representations from Structural Identity
• Modeling Relational Data with Graph Convolutional Networks
• node2vec: Scalable Feature Learning for Networks
• node2vec
• Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation
• LINE: Large-scale Information Network Embedding
• Epidemic processes in complex networks
• Exact analytical solutions of the Susceptible-Infected-Recovered (SIR) epidemic model and of the SIR model with equal death and birth rates
• Defining and Evaluating Network Communities based on Ground-truth
• Predicting Missing Links via Local Information
• Friends and neighbors on the Web