Coarse-to-Fine Sparse Sequential Recommendation

TL;DR

This paper introduces CaFe, a coarse-to-fine self-attention framework that models user intents and item interactions simultaneously, significantly improving recommendation quality on sparse datasets.

Contribution

It proposes a novel coarse-to-fine self-attention method that explicitly learns user intents from dense sequences to enhance item representations in recommendation systems.

Findings

CaFe outperforms state-of-the-art methods by 44.03% NDCG@5 on sparse datasets.

The framework effectively captures both coarse and fine-grained user dynamics.

Experiments demonstrate significant improvements in recommendation accuracy.

Abstract

Sequential recommendation aims to model dynamic user behavior from historical interactions. Self-attentive methods have proven effective at capturing short-term dynamics and long-term preferences. Despite their success, these approaches still struggle to model sparse data, on which they struggle to learn high-quality item representations. We propose to model user dynamics from shopping intents and interacted items simultaneously. The learned intents are coarse-grained and work as prior knowledge for item recommendation. To this end, we present a coarse-to-fine self-attention framework, namely CaFe, which explicitly learns coarse-grained and fine-grained sequential dynamics. Specifically, CaFe first learns intents from coarse-grained sequences which are dense and hence provide high-quality user intent representations. Then, CaFe fuses intent representations into item encoder outputs to obtain improved item representations. Finally, we infer recommended items based on representations of items and corresponding intents. Experiments on sparse datasets show that CaFe outperforms state-of-the-art self-attentive recommenders by 44.03% NDCG@5 on average.