# Sequence-level Semantic Representation Fusion for Recommender Systems

arXiv: https://arxiv.org/abs/2402.18166 · HTML: https://mlsanity.com/paper/2402.18166/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in MoE for recommender systems, one of 12 directions in Mixture-of-experts.
- First posted on arXiv 28 Feb 2024.

## Placed in

- Mixture-of-experts / [MoE for recommender systems](https://mlsanity.com/moe/moe-for-recommender-systems/)

## Built on by (most cited first, 10 of 10)

- [Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential Recommendation](https://mlsanity.com/paper/2501.14269/) (2025)
- [Structured Spectral Reasoning for Frequency-Adaptive Multimodal Recommendation](https://mlsanity.com/paper/2512.01372/) (2025)
- [Large Language Model Empowered Recommendation Meets All-domain Continual Pre-Training](https://mlsanity.com/paper/2504.08949/) (2025)
- [CogRec: A Cognitive Recommender Agent Fusing Large Language Models and Soar for Explainable Recommendation](https://mlsanity.com/paper/2512.24113/) (2025)
- [ImpReSS: Implicit Recommender System for Support Conversations](https://mlsanity.com/paper/2506.14231/) (2025)
- [STEP: Stepwise Curriculum Learning for Context-Knowledge Fusion in Conversational Recommendation](https://mlsanity.com/paper/2508.10669/) (2025)
- [CAMMSR: Category-Guided Attentive Mixture of Experts for Multimodal Sequential Recommendation](https://mlsanity.com/paper/2603.04320/) (2026)
- [VLM2Rec: Resolving Modality Collapse in Vision-Language Model Embedders for Multimodal Sequential Recommendation](https://mlsanity.com/paper/2603.17450/) (2026)
- [Aligning Multimodal Sequential Recommendations via Robust Direct Preference Optimization with Sparse MoE](https://mlsanity.com/paper/2603.29259/) (2026)
- [CAST: Modeling Semantic-Level Transitions for Complementary-Aware Sequential Recommendation](https://mlsanity.com/paper/2604.19414/) (2026)

## Abstract (arXiv)

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 (eg product title) and study how text features can be effectively fused with ID features in sequential recommendation. However, there exists distinct data characteristics for the two kinds of item features, making a direct fusion method (eg adding text and ID embeddings as item representation) become less effective. To address this issue, we propose a novel ul Text-Iul D semantic fusion approach for sequential ul Recommendation, namely our. The core idea of our approach is to conduct a sequence-level semantic fusion approach by better integrating global contexts. The key strategy lies in that we transform the text embeddings 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. In order to further improve the fusion performance, 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. Our implementation is available at this repository: textcolormagentaurlhttps://github.com/RUCAIBox/TedRec.