Graph-Sequential Alignment and Uniformity: Toward Enhanced Recommendation Systems

TL;DR

This paper introduces a novel recommendation framework that combines graph-based and sequential methods through shared embeddings and a specialized loss function, leading to improved performance over individual approaches.

Contribution

The paper presents a unified framework integrating GNN-based and sequential recommenders with a joint optimization strategy for enhanced recommendation accuracy.

Findings

Significantly outperforms individual methods on three datasets.

Achieves state-of-the-art recommendation results.

Demonstrates effective knowledge transfer between paradigms.

Abstract

Graph-based and sequential methods are two popular recommendation paradigms, each excelling in its domain but lacking the ability to leverage signals from the other. To address this, we propose a novel method that integrates both approaches for enhanced performance. Our framework uses Graph Neural Network (GNN)-based and sequential recommenders as separate submodules while sharing a unified embedding space optimized jointly. To enable positive knowledge transfer, we design a loss function that enforces alignment and uniformity both within and across submodules. Experiments on three real-world datasets demonstrate that the proposed method significantly outperforms using either approach alone and achieves state-of-the-art results. Our implementations are publicly available at https://github.com/YuweiCao-UIC/GSAU.git.