Memory Augmented Graph Neural Networks for Sequential Recommendation

TL;DR

This paper introduces MA-GNN, a memory-augmented graph neural network that effectively models both short-term and long-term user interests, as well as item co-occurrence patterns, to improve sequential recommendation accuracy.

Contribution

The paper presents a novel MA-GNN model combining graph neural networks and shared memory for better sequential user interest modeling in recommender systems.

Findings

Outperforms state-of-the-art methods on five real-world datasets

Effectively captures both short-term and long-term user interests

Improves Top-K recommendation performance

Abstract

The chronological order of user-item interactions can reveal time-evolving and sequential user behaviors in many recommender systems. The items that users will interact with may depend on the items accessed in the past. However, the substantial increase of users and items makes sequential recommender systems still face non-trivial challenges: (1) the hardness of modeling the short-term user interests; (2) the difficulty of capturing the long-term user interests; (3) the effective modeling of item co-occurrence patterns. To tackle these challenges, we propose a memory augmented graph neural network (MA-GNN) to capture both the long- and short-term user interests. Specifically, we apply a graph neural network to model the item contextual information within a short-term period and utilize a shared memory network to capture the long-range dependencies between items. In addition to the modeling of user interests, we employ a bilinear function to capture the co-occurrence patterns of related items. We extensively evaluate our model on five real-world datasets, comparing with several state-of-the-art methods and using a variety of performance metrics. The experimental results demonstrate the effectiveness of our model for the task of Top-K sequential recommendation.