Sequence-level Semantic Representation Fusion for Recommender Systems

Lanling Xu, Zhen Tian, Bingqian Li, Junjie Zhang, Daoyuan Wang, Hongyu Wang, Jinpeng Wang, Sheng Chen, Wayne Xin Zhao

Abstract: With the rapid development of recommender systems, there is increasing side information that can be employed to improve the recommendation performance. Specially, we focus on the utilization of the associated textual data of items (e.g., product title) and study how text features can be effectively fused with ID features in sequential recommendation. In this paper, we propose a novel <u> Te </u>xt-I<u> D </u> semantic fusion approach for sequential <u> Rec </u>ommendation, namely TedRec. The core idea is to conduct a sequence-level semantic fusion approach by integrating global contexts. The key strategy lies in that we transform the text and ID embeddings by Fourier Transform from time domain to frequency domain. In the frequency domain, the global sequential characteristics of the original sequences are inherently aggregated into the transformed representations, so that we can employ simple multiplicative operations to effectively fuse the two kinds of item features. Our fusion approach can be proved to have the same effects of contextual convolution, so as to achieving sequence-level semantic fusion. Further, we propose to enhance the discriminability of the text embeddings from the text encoder, by adaptively injecting positional information via a mixture-of-experts (MoE) modulation method. Both offline and online experiments demonstrate the effectiveness of our approach.