Evolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendation

TL;DR

This paper introduces GNG-ODE, a continuous-time neural ODE model for session-based recommendation that captures evolving user preferences more accurately than discrete models.

Contribution

It extends neural ODEs to dynamic session graphs with a novel t-Alignment technique, enabling better modeling of preference evolution.

Findings

GNG-ODE outperforms baseline models on benchmark datasets.

The model effectively captures fine-grained preference changes.

Continuous-time modeling improves recommendation accuracy.

Abstract

Session-based recommendation (SBR) aims to predict the user next action based on the ongoing sessions. Recently, there has been an increasing interest in modeling the user preference evolution to capture the fine-grained user interests. While latent user preferences behind the sessions drift continuously over time, most existing approaches still model the temporal session data in discrete state spaces, which are incapable of capturing the fine-grained preference evolution and result in sub-optimal solutions. To this end, we propose Graph Nested GRU ordinary differential equation (ODE), namely GNG-ODE, a novel continuum model that extends the idea of neural ODEs to continuous-time temporal session graphs. The proposed model preserves the continuous nature of dynamic user preferences, encoding both temporal and structural patterns of item transitions into continuous-time dynamic embeddings. As the existing ODE solvers do not consider graph structure change and thus cannot be directly applied to the dynamic graph, we propose a time alignment technique, called t-Alignment, to align the updating time steps of the temporal session graphs within a batch. Empirical results on three benchmark datasets show that GNG-ODE significantly outperforms other baselines.