Sequential Recommendation with Controllable Diversification: Representation Degeneration and Diversity

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fan, Ziwei, Liu, Zhiwei, Peng, Hao, Yu, Philip S.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929426735824896
author Fan, Ziwei
Liu, Zhiwei
Peng, Hao
Yu, Philip S.
author_facet Fan, Ziwei
Liu, Zhiwei
Peng, Hao
Yu, Philip S.
contents Sequential recommendation (SR) models the dynamic user preferences and generates the next-item prediction as the affinity between the sequence and items, in a joint latent space with low dimensions (i.e., the sequence and item embedding space). Both sequence and item representations suffer from the representation degeneration issue due to the user/item long-tail distributions, where tail users/ items are indistinguishably distributed as a narrow cone in the latent space. We argue that the representation degeneration issue is the root cause of insufficient recommendation diversity in existing SR methods, impairing the user potential exploration and further worsening the echo chamber issue. In this work, we first disclose the connection between the representation degeneration and recommendation diversity, in which severer representation degeneration indicates lower recommendation diversity. We then propose a novel Singular sPectrum sMoothing regularization for Recommendation (SPMRec), which acts as a controllable surrogate to alleviate the degeneration and achieve the balance between recommendation diversity and performance. The proposed smoothing regularization alleviates the degeneration by maximizing the area under the singular value curve, which is also the diversity surrogate. We conduct experiments on four benchmark datasets to demonstrate the superiority of SPMRec, and show that the proposed singular spectrum smoothing can control the balance of recommendation performance and diversity simultaneously.
format Preprint
id arxiv_https___arxiv_org_abs_2306_11986
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Sequential Recommendation with Controllable Diversification: Representation Degeneration and Diversity
Fan, Ziwei
Liu, Zhiwei
Peng, Hao
Yu, Philip S.
Information Retrieval
Machine Learning
Sequential recommendation (SR) models the dynamic user preferences and generates the next-item prediction as the affinity between the sequence and items, in a joint latent space with low dimensions (i.e., the sequence and item embedding space). Both sequence and item representations suffer from the representation degeneration issue due to the user/item long-tail distributions, where tail users/ items are indistinguishably distributed as a narrow cone in the latent space. We argue that the representation degeneration issue is the root cause of insufficient recommendation diversity in existing SR methods, impairing the user potential exploration and further worsening the echo chamber issue. In this work, we first disclose the connection between the representation degeneration and recommendation diversity, in which severer representation degeneration indicates lower recommendation diversity. We then propose a novel Singular sPectrum sMoothing regularization for Recommendation (SPMRec), which acts as a controllable surrogate to alleviate the degeneration and achieve the balance between recommendation diversity and performance. The proposed smoothing regularization alleviates the degeneration by maximizing the area under the singular value curve, which is also the diversity surrogate. We conduct experiments on four benchmark datasets to demonstrate the superiority of SPMRec, and show that the proposed singular spectrum smoothing can control the balance of recommendation performance and diversity simultaneously.
title Sequential Recommendation with Controllable Diversification: Representation Degeneration and Diversity
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2306.11986