Skip to content
Preprint

LSF-SR: Latent Semantic Fusion for Sequential Recommendation via Flow-based Conditional Variational Autoencoders

Sep 2026 · 0 citations · 30 references
Computer Science

TL;DR

Latent Semantic Fusion for Sequential Recommendation via Flow-based Conditional Variational Autoencoders (LSF-SR), a novel framework that uses a Conditional Variational Autoencoder with Normalizing Flows to fuse item ID embeddings and LLM-generated semantic signals.

Abstract

Sequential recommendation aims to predict users'future interests from their historical interactions. Although Large Language Models (LLMs) capture rich item semantics, existing methods often struggle to align collaborative signals with textual semantic knowledge. As a result, the learned item representations fail to capture the complementary strengths of both signals, leading to suboptimal recommendation quality. To address this limitation, we propose Latent Semantic Fusion for Sequential Recommendation via Flow-based Conditional Variational Autoencoders (LSF-SR), a novel framework that uses a Conditional Variational Autoencoder (CVAE) with Normalizing Flows to fuse item ID embeddings and LLM-generated semantic signals. At the core of LSF-SR is a conditional fusion module augmented with planar or radial flows. This module learns a flexible latent space that encourages items with similar semantic profiles to cluster together within the latent manifold. Through extensive experiments on five public benchmark datasets, we demonstrate that LSF-SR consistently outperforms state-of-the-art baselines, achieving gains of up to 12.98% and 14.13% in Recall@20 and NDCG@20, respectively.

View source

Similar papers

Book Open access Sep 2026

Addressing Cross-Stage Decoupling of Semantic and Collaborative Signals in Generative Recommendation

This work proposes SCRec, a general framework that enhances cross-stage coherence through bidirectional information supplementation and aligns semantic and collaborative signals and enhances cross-stage information coherence, with minimal additional training and inference costs.

Jia-Yi Dan, Wei-Jian Li, Yong-Qi Liu et al. · 0 citations
Conference Open access Sep 2026

Bridging the Semantic Gap: Leveraging LLMs for Hierarchical Interest Evolution in Sequential Recommendation

The Hierarchical Semantic Interest Evolution Network (HSIEN), a novel generative-discriminative framework that significantly alleviates modality misalignment and enhances CTR prediction performance through feature complementarity, is proposed.

Yi-Fan Cao, Rui Wu, Xiang Wang et al. · 0 citations
#large language models Review Open access Sep 2026

PALRec: Large Language Model-Based Sequential Recommendation with Parameter-Preserving Augmentation

PALRec is proposed, a parameter-preserving augmentation framework that equips an LLM with recommendation capabilities while keeping its original parameters fixed and consistently outperforms fully fine-tuned counterparts in recommendation accuracy while preserving the LLM’s pre-trained knowledge.

Hyunsoo Na, Minseok Gang, Sang-goo Lee et al. · 0 citations
Conference Aug 2026

SeRel-LightFM: Bridging Semantic and Relational Representations for Sparse Hybrid Recommendation

Data sparsity remains a major obstacle for recommender systems because conventional collaborative filtering methods rely heavily on observed user–item interactions and often fail to exploit richer semantic and relational signals. To address this limitation, we propose SeRel-LightFM, a knowledge-aware hybrid recommendat...

M. Pham, V. Vu, Hung-Nghiep Tran · 0 citations
Sep 2026

X-Rec Technical Report

Recent advances in generative modeling have reshaped recommender systems by formulating recommendation as a next-item generation problem. Existing retrieval approaches primarily follow two paradigms: user-to-item (U2I) methods represent user context using one or a few deterministic embeddings, which limits the ability...

Cheng-Lei Shen, Chen-Zhe Huang, Dong Jiang et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.