Revisiting Neighborhood-based Link Prediction for Collaborative Filtering

TL;DR

This paper introduces a simple, non-deep learning link prediction model for collaborative filtering that significantly outperforms current GNN-based methods by focusing on local graph structures without node modeling.

Contribution

It proposes a new linkage score and an iterative degree update process for bipartite graphs, emphasizing link prediction over node embedding in recommendation systems.

Findings

Over 60% improvement in Recall and NDCG on Amazon-Book.

Outperforms state-of-the-art GNN-based CF models on four benchmarks.

Demonstrates the effectiveness of simple link prediction methods in recommendation tasks.

Abstract

Collaborative filtering (CF) is one of the most successful and fundamental techniques in recommendation systems. In recent years, Graph Neural Network (GNN)-based CF models, such as NGCF [31], LightGCN [10] and GTN [9] have achieved tremendous success and significantly advanced the state-of-the-art. While there is a rich literature of such works using advanced models for learning user and item representations separately, item recommendation is essentially a link prediction problem between users and items. Furthermore, while there have been early works employing link prediction for collaborative filtering [5, 6], this trend has largely given way to works focused on aggregating information from user and item nodes, rather than modeling links directly. In this paper, we propose a new linkage (connectivity) score for bipartite graphs, generalizing multiple standard link prediction methods. We combine this new score with an iterative degree update process in the user-item interaction bipartite graph to exploit local graph structures without any node modeling. The result is a simple, non-deep learning model with only six learnable parameters. Despite its simplicity, we demonstrate our approach significantly outperforms existing state-of-the-art GNN-based CF approaches on four widely used benchmarks. In particular, on Amazon-Book, we demonstrate an over 60% improvement for both Recall and NDCG. We hope our work would invite the community to revisit the link prediction aspect of collaborative filtering, where significant performance gains could be achieved through aligning link prediction with item recommendations.