Graph Neural Patching for Cold-Start Recommendations

TL;DR

This paper introduces GNP, a novel GNN framework that improves cold-start recommendations without compromising warm user/item performance, validated by extensive experiments on benchmark datasets.

Contribution

The paper proposes GNP, a dual-function GNN framework that effectively addresses cold-start recommendation challenges while maintaining warm recommendation quality.

Findings

GNP outperforms existing methods on benchmark datasets.

GNP effectively models both warm and cold user/item recommendations.

Experimental results demonstrate GNP's superior recommendation accuracy.

Abstract

The cold start problem in recommender systems remains a critical challenge. Current solutions often train hybrid models on auxiliary data for both cold and warm users/items, potentially degrading the experience for the latter. This drawback limits their viability in practical scenarios where the satisfaction of existing warm users/items is paramount. Although graph neural networks (GNNs) excel at warm recommendations by effective collaborative signal modeling, they haven't been effectively leveraged for the cold-start issue within a user-item graph, which is largely due to the lack of initial connections for cold user/item entities. Addressing this requires a GNN adept at cold-start recommendations without sacrificing performance for existing ones. To this end, we introduce Graph Neural Patching for Cold-Start Recommendations (GNP), a customized GNN framework with dual functionalities: GWarmer for modeling collaborative signal on existing warm users/items and Patching Networks for simulating and enhancing GWarmer's performance on cold-start recommendations. Extensive experiments on three benchmark datasets confirm GNP's superiority in recommending both warm and cold users/items.