LLM-based Bi-level Multi-interest Learning Framework for Sequential Recommendation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qiao, Shutong, Gao, Chen, Yuan, Wei, Li, Yong, Yin, Hongzhi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918012450242560
author Qiao, Shutong
Gao, Chen
Yuan, Wei
Li, Yong
Yin, Hongzhi
author_facet Qiao, Shutong
Gao, Chen
Yuan, Wei
Li, Yong
Yin, Hongzhi
contents Sequential recommendation (SR) leverages users' dynamic preferences, with recent advances incorporating multi-interest learning to model diverse user interests. However, most multi-interest SR models rely on noisy, sparse implicit feedback, limiting recommendation accuracy. Large language models (LLMs) offer robust reasoning on low-quality data but face high computational costs and latency challenges for SR integration. We propose a novel LLM-based multi-interest SR framework combining implicit behavioral and explicit semantic perspectives. It includes two modules: the Implicit Behavioral Interest Module (IBIM), which learns from user behavior using a traditional SR model, and the Explicit Semantic Interest Module (ESIM), which uses clustering and prompt-engineered LLMs to extract semantic multi-interest representations from informative samples. Semantic insights from ESIM enhance IBIM's behavioral representations via modality alignment and semantic prediction tasks. During inference, only IBIM is used, ensuring efficient, LLM-free recommendations. Experiments on four real-world datasets validate the framework's effectiveness and practicality.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09410
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LLM-based Bi-level Multi-interest Learning Framework for Sequential Recommendation
Qiao, Shutong
Gao, Chen
Yuan, Wei
Li, Yong
Yin, Hongzhi
Information Retrieval
Sequential recommendation (SR) leverages users' dynamic preferences, with recent advances incorporating multi-interest learning to model diverse user interests. However, most multi-interest SR models rely on noisy, sparse implicit feedback, limiting recommendation accuracy. Large language models (LLMs) offer robust reasoning on low-quality data but face high computational costs and latency challenges for SR integration. We propose a novel LLM-based multi-interest SR framework combining implicit behavioral and explicit semantic perspectives. It includes two modules: the Implicit Behavioral Interest Module (IBIM), which learns from user behavior using a traditional SR model, and the Explicit Semantic Interest Module (ESIM), which uses clustering and prompt-engineered LLMs to extract semantic multi-interest representations from informative samples. Semantic insights from ESIM enhance IBIM's behavioral representations via modality alignment and semantic prediction tasks. During inference, only IBIM is used, ensuring efficient, LLM-free recommendations. Experiments on four real-world datasets validate the framework's effectiveness and practicality.
title LLM-based Bi-level Multi-interest Learning Framework for Sequential Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2411.09410