Hierarchical BiGraph Neural Network as Recommendation Systems

TL;DR

This paper introduces the Hierarchical BiGraph Neural Network (HBGNN), a novel GNN-based recommendation system that effectively models sparse user-item data using a hierarchical bigraph framework, demonstrating competitive results.

Contribution

The paper presents a new hierarchical GNN approach, HBGNN, structured with a bigraph framework to improve recommendation performance on sparse datasets.

Findings

Competitive performance with existing recommendation methods

Effective handling of sparse user-item data

Good transferability across datasets

Abstract

Graph neural networks emerge as a promising modeling method for applications dealing with datasets that are best represented in the graph domain. In specific, developing recommendation systems often require addressing sparse structured data which often lacks the feature richness in either the user and/or item side and requires processing within the correct context for optimal performance. These datasets intuitively can be mapped to and represented as networks or graphs. In this paper, we propose the Hierarchical BiGraph Neural Network (HBGNN), a hierarchical approach of using GNNs as recommendation systems and structuring the user-item features using a bigraph framework. Our experimental results show competitive performance with current recommendation system methods and transferability.