Revisiting scalable sequential recommendation with Multi-Embedding Approach and Mixture-of-Experts

• URL: http://arxiv.org/abs/2510.25285v1
• Date: Wed, 29 Oct 2025 08:42:15 GMT
• Title: Revisiting scalable sequential recommendation with Multi-Embedding Approach and Mixture-of-Experts
• Authors: Qiushi Pan, Hao Wang, Guoyuan An, Luankang Zhang, Wei Guo, Yong Liu,
• Abstract summary: We propose Fuxi-MME, a framework that integrates a multi-embedding strategy with a Mixture-of-Experts (MoE) architecture.<n>Specifically, to efficiently capture diverse item characteristics in a decoupled manner, we decompose the conventional single embedding matrix into several lower-dimensional embedding matrices.
• Score: 15.976682531132676
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recommendation systems, how to effectively scale up recommendation models has been an essential research topic. While significant progress has been made in developing advanced and scalable architectures for sequential recommendation(SR) models, there are still challenges due to items' multi-faceted characteristics and dynamic item relevance in the user context. To address these issues, we propose Fuxi-MME, a framework that integrates a multi-embedding strategy with a Mixture-of-Experts (MoE) architecture. Specifically, to efficiently capture diverse item characteristics in a decoupled manner, we decompose the conventional single embedding matrix into several lower-dimensional embedding matrices. Additionally, by substituting relevant parameters in the Fuxi Block with an MoE layer, our model achieves adaptive and specialized transformation of the enriched representations. Empirical results on public datasets show that our proposed framework outperforms several competitive baselines.

Related papers

• CAMMSR: Category-Guided Attentive Mixture of Experts for Multimodal Sequential Recommendation [23.478610632707728]
  We propose a Category-guided Attentive Mixture of Experts model for Multimodal Sequential Recommendation.<n>At its core, CAMMSR introduces a category-guided attentive mixture of experts module, which learns specialized item representations from multiple perspectives.<n>Experiments on four public datasets demonstrate that CAMMSR consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-04T17:39:35Z)
• Reconstructing Content via Collaborative Attention to Improve Multimodal Embedding Quality [59.651410243721045]
  CoCoA is a Content reconstruction pre-training paradigm based on Collaborative Attention for multimodal embedding optimization.<n>We introduce an EOS-based reconstruction task, encouraging the model to reconstruct input from the corresponding EOS> embeddings.<n>Experiments on MMEB-V1 demonstrate that CoCoA built upon Qwen2-VL and Qwen2.5-VL significantly improves embedding quality.
  arXiv  Detail & Related papers  (2026-03-02T05:34:45Z)
• Multimodal Generative Recommendation for Fusing Semantic and Collaborative Signals [17.608491612845306]
  Sequential recommender systems rank relevant items by modeling a user's interaction history and computing the inner product between the resulting user representation and stored item embeddings.<n>To avoid the significant memory overhead of storing large item sets, the generative recommendation paradigm instead models each item as a series of discrete semantic codes.<n>These methods have yet to surpass traditional sequential recommenders on large item sets, limiting their adoption in the very scenarios they were designed to address.<n>We propose MSCGRec, a Multimodal Semantic and Collaborative Generative Recommender.
  arXiv  Detail & Related papers  (2026-02-03T16:39:35Z)
• Gated Multimodal Graph Learning for Personalized Recommendation [9.466822984141086]
  Multimodal recommendation has emerged as a promising solution to alleviate the cold-start and sparsity problems in collaborative filtering.<n>We propose RLMultimodalRec, a lightweight and modular recommendation framework that combines graph-based user modeling with adaptive multimodal item encoding.
  arXiv  Detail & Related papers  (2025-05-30T16:57:17Z)
• Learning Item Representations Directly from Multimodal Features for Effective Recommendation [51.49251689107541]
  multimodal recommender systems predominantly leverage Bayesian Personalized Ranking (BPR) optimization to learn item representations.<n>We propose a novel model (i.e., LIRDRec) that learns item representations directly from multimodal features to augment recommendation performance.
  arXiv  Detail & Related papers  (2025-05-08T05:42:22Z)
• Matrix Factorization with Dynamic Multi-view Clustering for Recommender System [5.807887214293438]
  Matrix factorization (MF) is a cornerstone of recommender systems.<n>MFDMC is a unified framework that balances efficient end-to-end training with comprehensive utilization of web-scale data.
  arXiv  Detail & Related papers  (2025-04-20T10:47:21Z)
• Joint Modeling in Recommendations: A Survey [46.000357352884926]
  Joint modeling approaches are central to overcoming limitations by integrating diverse tasks, scenarios, modalities, and behaviors in the recommendation process.<n>We define the scope of joint modeling through four distinct dimensions: multi-task, multi-scenario, multi-modal, and multi-behavior modeling.<n>We highlight several promising avenues for future exploration in joint modeling for recommendations and provide a concise conclusion to our findings.
  arXiv  Detail & Related papers  (2025-02-28T16:14:00Z)
• CADMR: Cross-Attention and Disentangled Learning for Multimodal Recommender Systems [0.6037276428689637]
  We propose CADMR, a novel autoencoder-based multimodal recommender system framework.<n>We evaluate CADMR on three benchmark datasets, demonstrating significant performance improvements over state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-12-03T09:09:52Z)
• Learning Multi-Aspect Item Palette: A Semantic Tokenization Framework for Generative Recommendation [55.99632509895994]
  We introduce LAMIA, a novel approach for multi-aspect semantic tokenization.<n>Unlike RQ-VAE, which uses a single embedding, LAMIA learns an item palette''--a collection of independent and semantically parallel embeddings.<n>Our results demonstrate significant improvements in recommendation accuracy over existing methods.
  arXiv  Detail & Related papers  (2024-09-11T13:49:48Z)
• Towards Bridging the Cross-modal Semantic Gap for Multi-modal Recommendation [12.306686291299146]
  Multi-modal recommendation greatly enhances the performance of recommender systems. Most existing multi-modal recommendation models exploit multimedia information propagation processes to enrich item representations. We propose a novel framework to bridge the semantic gap between modalities and extract fine-grained multi-view semantic information.
  arXiv  Detail & Related papers  (2024-07-07T15:56:03Z)
• LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations [51.76373105981212]
  Reranking is a critical component in recommender systems, playing an essential role in refining the output of recommendation algorithms.<n>We introduce a comprehensive reranking framework, designed to seamlessly integrate various reranking criteria.<n>A customizable input mechanism is also integrated, enabling the tuning of the language model's focus to meet specific reranking needs.
  arXiv  Detail & Related papers  (2024-06-18T09:29:18Z)
• Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima [54.06000767038741]
  We analyze multimodal recommender systems from the novel perspective of flat local minima. We propose a concise yet effective gradient strategy called Mirror Gradient (MG) We find that the proposed MG can complement existing robust training methods and be easily extended to diverse advanced recommendation models.
  arXiv  Detail & Related papers  (2024-02-17T12:27:30Z)
• Embedding in Recommender Systems: A Survey [54.55152033023537]
  This survey presents a comprehensive analysis of advances in recommender system embedding techniques.<n>In matrix-based scenarios, collaborative filtering generates embeddings that effectively model user-item preferences.<n>We introduce emerging approaches, including AutoML, hashing techniques, and quantization methods, to enhance performance.
  arXiv  Detail & Related papers  (2023-10-28T06:31:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.