A Community-Enhanced Graph Representation Model for Link Prediction

TL;DR

CELP introduces a Community-Enhanced Link Prediction framework that leverages community structure as a global prior to jointly refine graph topology and edge representations. It combines three modules—Global Enhancement for community-aware encodings, Structure Enhancement for confidence-guided edge completion/pruning, and Local Representation Enhancement for multi-scale triple-relational edge features—along with a joint loss that includes a structural contrastive term. The method demonstrates superior link prediction performance across six real datasets, with notable gains on smaller graphs and competitive results on larger ones, validating the value of explicit community information in capturing both local and global graph structure. By explicitly modeling community-level relations and multi-hop signals, CELP improves robustness to over-smoothing and incomplete graphs, offering a scalable, interpretable approach for structure-aware link prediction.

Abstract

Although Graph Neural Networks (GNNs) have become the dominant approach for graph representation learning, their performance on link prediction tasks does not always surpass that of traditional heuristic methods such as Common Neighbors and Jaccard Coefficient. This is mainly because existing GNNs tend to focus on learning local node representations, making it difficult to effectively capture structural relationships between node pairs. Furthermore, excessive reliance on local neighborhood information can lead to over-smoothing. Prior studies have shown that introducing global structural encoding can partially alleviate this issue. To address these limitations, we propose a Community-Enhanced Link Prediction (CELP) framework that incorporates community structure to jointly model local and global graph topology. Specifically, CELP enhances the graph via community-aware, confidence-guided edge completion and pruning, while integrating multi-scale structural features to achieve more accurate link prediction. Experimental results across multiple benchmark datasets demonstrate that CELP achieves superior performance, validating the crucial role of community structure in improving link prediction accuracy.

Figures (8)

• Figure 1: Illustrative Example of the Community Detection Algorithm. By applying a community detection algorithm, a complex graph can be partitioned into different communities, where nodes within the same community are more densely connected, while connections with nodes from different communities are relatively sparse.
• Figure 2: Framework of CELP. Community detection is first performed on the original graph, and the PageRank centrality is utilized to identify the central node within each community, which serves as the foundation for constructing global node representations. Next, prior probabilities are introduced to enhance and complete the graph structure, effectively mitigating the issue of graph incompleteness. Finally, by integrating the local neighborhood features, path information, and cross-community collaborative features of target node pairs, a more effective edge representation is constructed, thereby improving the performance of link prediction.
• Figure 3: Ablation study results of CELP on the structure enhancement module. "w/o add" denotes removing the edge addition strategy, and "w/o remove" denotes removing the edge removal strategy.
• Figure 4: The impact of the number of communities on model performance.
• Figure 5: The impact of the number of layers on model performance.