TY - GEN
T1 - Modeling Field-Level Factor Interactions for Fashion Recommendation
AU - Ding, Yujuan
AU - Mok, P. Y.
AU - Yang, Xun
AU - Zhou, Yanghong
N1 - Funding Information:
The work described in this paper was supported by grants from the Research Grants Council of the Hong Kong Special Administrative Region, China (Project No. 152161/17E and 152112/19E) and partly supported by the Innovation and Technology Commission of Hong Kong under grant ITP/028/21TP. We also appreciate the fashion recognition API service provided by Visenze.
Publisher Copyright:
© 2022 IEEE.
PY - 2022/8/26
Y1 - 2022/8/26
N2 - 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.
AB - 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.
KW - Attribute Incorporation
KW - Factor Interaction Modeling
KW - Personalized Fashion Recommendation
UR - http://www.scopus.com/inward/record.url?scp=85137722730&partnerID=8YFLogxK
U2 - 10.1109/ICME52920.2022.9859989
DO - 10.1109/ICME52920.2022.9859989
M3 - Conference article published in proceeding or book
AN - SCOPUS:85137722730
SN - 9781665485647
VL - 2022-July
T3 - Proceedings - IEEE International Conference on Multimedia and Expo
BT - ICME 2022 - IEEE International Conference on Multimedia and Expo 2022, Proceedings
PB - IEEE Computer Society
T2 - 2022 IEEE International Conference on Multimedia and Expo, ICME 2022
Y2 - 18 July 2022 through 22 July 2022
ER -