RichGNN: Attribute-enriched graph neural network for optimized e-commerce recommendations

Abderaouf Bahi

doi:10.1007/s10115-026-02737-x

RichGNN: Attribute-enriched graph neural network for optimized e-commerce recommendations

2026-03-27

0

PRE

AI

DOI：10.1007/s10115-026-02737-x

Original

Original request for help

Save

Abstract

En 中文

Real-world e-commerce and media platforms are characterized by sparse feedback, incomplete attributes, and heterogeneous side information, which substantially limit the expressive power of conventional graph-based recommenders. In this work, we propose RichGNN, an attribute-enriched graph neural network (GNN) designed to jointly address interaction sparsity and attribute incompleteness through a unified representation learning framework. By combining structural signals from the interaction graph with enriched semantic information, the proposed model learns a more coherent and expressive latent space that better captures user preferences and item characteristics. Extensive experiments conducted on two widely used benchmarks, MovieLens 100K and MovieLens 1 M, demonstrate the effectiveness of the proposed framework compared to strong baselines achieving consistent and significant improvements, including a relative gain of +5.53% in Recall@20 and +4.64% in NDCG@20 on MovieLens 1 M, as well as +3.99% in Recall@20 and +2.88% in NDCG@20 on MovieLens 100K. Further ablation studies confirm the critical role of attribute enrichment, generative attribute completion, and attention-based fusion in driving these improvements. The results highlight RichGNN as a robust and effective solution for attribute-aware recommendation under sparse and incomplete data conditions.

Keywords:

Recommender system

Graph neural network

Variational autoencoder

Enriched attribute

E-commerce.

RichGNN: Attribute-enriched graph neural network for optimized e-commerce recommendations

Abstract

Journal

Organization