Session-based recommendation: Learning multi-dimension interests via a multi-head attention graph neural network

Abstract

In a recent study, it was shown that, with batch training of a graph neural network, it is possible to recommend suitable items for users. Although the method has obtained item embedding and considered the complex transitions between items, there is no multi-dimensional focus on the users’ interests and preferences. In this paper, we propose a multi-head attention graph neural network (MAE-GNN) for session-based recommendation by combining a dual-gated graph neural network and multi-head attention mechanisms. MAE-GNN can select important node information and extract users’ interests and preferences from multiple dimensions. Experimental evaluation has been conducted to show that, compared with the state-of-the-art methods, the proposed model has significant improvement in term of P@K and MRR@K for session-based recommendation.