DAGNN: Demand-aware Graph Neural Networks for Session-based Recommendation

TL;DR

This paper introduces DAGNN, a demand-aware graph neural network for session-based recommendations that models user demands to improve recommendation accuracy, achieving state-of-the-art results on real-world datasets.

Contribution

The paper proposes a novel demand modeling component and demand-aware GNN architecture that explicitly captures user demands from session data, enhancing recommendation quality.

Findings

DAGNN outperforms existing models on multiple datasets.

Demand modeling improves recommendation relevance.

Mutual information loss enhances embedding quality.

Abstract

Session-based recommendations have been widely adopted for various online video and E-commerce Websites. Most existing approaches are intuitively proposed to discover underlying interests or preferences out of the anonymous session data. This apparently ignores the fact these sequential behaviors usually reflect session user's potential demand, i.e., a semantic level factor, and therefore how to estimate underlying demands from a session is challenging. To address aforementioned issue, this paper proposes a demand-aware graph neural networks (DAGNN). Particularly, a demand modeling component is designed to first extract session demand and the underlying multiple demands of each session is estimated using the global demand matrix. Then, the demand-aware graph neural network is designed to extract session demand graph to learn the demand-aware item embedddings for the later recommendations. The mutual information loss is further designed to enhance the quality of the learnt embeddings. Extensive experiments are evaluated on several real-world datasets and the proposed model achieves the SOTA model performance.