RaSeRec: Retrieval-Augmented Sequential Recommendation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhao, Xinping, Hu, Baotian, Zhong, Yan, Huang, Shouzheng, Zheng, Zihao, Wang, Meng, Wang, Haofen, Zhang, Min
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913689549930496
author Zhao, Xinping
Hu, Baotian
Zhong, Yan
Huang, Shouzheng
Zheng, Zihao
Wang, Meng
Wang, Haofen
Zhang, Min
author_facet Zhao, Xinping
Hu, Baotian
Zhong, Yan
Huang, Shouzheng
Zheng, Zihao
Wang, Meng
Wang, Haofen
Zhang, Min
contents Although prevailing supervised and self-supervised learning augmented sequential recommendation (SeRec) models have achieved improved performance with powerful neural network architectures, we argue that they still suffer from two limitations: (1) Preference Drift, where models trained on past data can hardly accommodate evolving user preference; and (2) Implicit Memory, where head patterns dominate parametric learning, making it harder to recall long tails. In this work, we explore retrieval augmentation in SeRec, to address these limitations. Specifically, we propose a Retrieval-Augmented Sequential Recommendation framework, named RaSeRec, the main idea of which is to maintain a dynamic memory bank to accommodate preference drifts and retrieve relevant memories to augment user modeling explicitly. It consists of two stages: (i) collaborative-based pre-training, which learns to recommend and retrieve; (ii) retrieval-augmented fine-tuning, which learns to leverage retrieved memories. Extensive experiments on three datasets fully demonstrate the superiority and effectiveness of RaSeRec. The implementation code is available at https://github.com/HITsz-TMG/RaSeRec.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18378
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RaSeRec: Retrieval-Augmented Sequential Recommendation
Zhao, Xinping
Hu, Baotian
Zhong, Yan
Huang, Shouzheng
Zheng, Zihao
Wang, Meng
Wang, Haofen
Zhang, Min
Information Retrieval
Although prevailing supervised and self-supervised learning augmented sequential recommendation (SeRec) models have achieved improved performance with powerful neural network architectures, we argue that they still suffer from two limitations: (1) Preference Drift, where models trained on past data can hardly accommodate evolving user preference; and (2) Implicit Memory, where head patterns dominate parametric learning, making it harder to recall long tails. In this work, we explore retrieval augmentation in SeRec, to address these limitations. Specifically, we propose a Retrieval-Augmented Sequential Recommendation framework, named RaSeRec, the main idea of which is to maintain a dynamic memory bank to accommodate preference drifts and retrieve relevant memories to augment user modeling explicitly. It consists of two stages: (i) collaborative-based pre-training, which learns to recommend and retrieve; (ii) retrieval-augmented fine-tuning, which learns to leverage retrieved memories. Extensive experiments on three datasets fully demonstrate the superiority and effectiveness of RaSeRec. The implementation code is available at https://github.com/HITsz-TMG/RaSeRec.
title RaSeRec: Retrieval-Augmented Sequential Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2412.18378