Modeling Field-level Factor Interactions for Fashion Recommendation

TL;DR

This paper introduces AFFIG, an attention-based graph model that captures field-level factor interactions to improve personalized fashion recommendations, addressing data sparsity and diversity challenges.

Contribution

It proposes a novel attentional factor field interaction graph that models both user-factor and cross-field interactions for enhanced recommendation accuracy.

Findings

AFFIG outperforms baseline models on three fashion datasets.

Model effectively captures the influence of different factor fields.

Attention mechanism improves the aggregation of cross-field interactions.

Abstract

Personalized fashion recommendation aims to explore patterns from historical interactions between users and fashion items and thereby predict the future ones. It is challenging due to the sparsity of the interaction data and the diversity of user preference in fashion. To tackle the challenge, this paper investigates multiple factor fields in fashion domain, such as colour, style, brand, and tries to specify the implicit user-item interaction into field level. Specifically, an attentional factor field interaction graph (AFFIG) approach is proposed which models both the user-factor interactions and cross-field factors interactions for predicting the recommendation probability at specific field. In addition, an attention mechanism is equipped to aggregate the cross-field factor interactions for each field. Extensive experiments have been conducted on three E-Commerce fashion datasets and the results demonstrate the effectiveness of the proposed method for fashion recommendation. The influence of various factor fields on recommendation in fashion domain is also discussed through experiments.