Addressing Cold Start in Recommender Systems with Hierarchical Graph Neural Networks

TL;DR

This paper introduces a novel hierarchical graph neural network approach to mitigate the cold start problem in recommender systems, demonstrating improved prediction accuracy on large-scale datasets.

Contribution

The work presents a new GNN architecture leveraging item hierarchy graphs specifically designed to address cold start issues in recommender systems.

Findings

Outperforms state-of-the-art methods in forecasting quality

Achieves better results on multiple large-scale datasets

Maintains comparable computational efficiency

Abstract

Recommender systems have become an essential instrument in a wide range of industries to personalize the user experience. A significant issue that has captured both researchers' and industry experts' attention is the cold start problem for new items. In this work, we present a graph neural network recommender system using item hierarchy graphs and a bespoke architecture to handle the cold start case for items. The experimental study on multiple datasets and millions of users and interactions indicates that our method achieves better forecasting quality than the state-of-the-art with a comparable computational time.