Memory-augmented meta-learning on meta-path for fast adaptation cold-start recommendation

Personalised recommendation is a difficult problem that has received a lot of attention to academia and industry. Because of the sparse user–item interaction, cold-start recommendation has been a particularly difficult problem. Some efforts have been made to solve the cold-start problem by using mod...

Full description

Saved in:
Bibliographic Details
Main Authors: Tianyuan Li, Xin Su, Wei Liu, Wei Liang, Meng-Yen Hsieh, Zhuhui Chen, XuChong Liu, Hong Zhang
Format: Article
Language:English
Published: Taylor & Francis Group 2022-12-01
Series:Connection Science
Subjects:
Online Access:http://dx.doi.org/10.1080/09540091.2021.1996537
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850225240215388160
author Tianyuan Li
Xin Su
Wei Liu
Wei Liang
Meng-Yen Hsieh
Zhuhui Chen
XuChong Liu
Hong Zhang
author_facet Tianyuan Li
Xin Su
Wei Liu
Wei Liang
Meng-Yen Hsieh
Zhuhui Chen
XuChong Liu
Hong Zhang
author_sort Tianyuan Li
collection DOAJ
description Personalised recommendation is a difficult problem that has received a lot of attention to academia and industry. Because of the sparse user–item interaction, cold-start recommendation has been a particularly difficult problem. Some efforts have been made to solve the cold-start problem by using model-agnostic meta-learning on the level of the model and heterogeneous information networks on the level of data. Moreover, using the memory-augmented meta-optimisation method effectively prevents the meta-learning model from entering the local optimum. As a result, this paper proposed memory-augmented meta-learning on meta-path, a new meta-learning method that addresses the cold-start recommendation on the meta-path furthered. The meta-path builds at the data level to enrich the relevant semantic information of the data. To achieve fast adaptation, semantic-specific memory is utilised to conduct the model with semantic parameter initialisation, and the method is optimised by a meta-optimisation method. We put this method to the test using two widely used recommended data set and three cold-start scenarios. The experimental results demonstrate the efficiency of our proposed method.
format Article
id doaj-art-577d8355a6064e46a1dfbaf644632e6a
institution OA Journals
issn 0954-0091
1360-0494
language English
publishDate 2022-12-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-577d8355a6064e46a1dfbaf644632e6a2025-08-20T02:05:25ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-0134130131810.1080/09540091.2021.19965371996537Memory-augmented meta-learning on meta-path for fast adaptation cold-start recommendationTianyuan Li0Xin Su1Wei Liu2Wei Liang3Meng-Yen Hsieh4Zhuhui Chen5XuChong Liu6Hong Zhang7Xiangtan UniversityHunan Provincial Key Laboratory of Network Investigational Technology, Hunan Police AcademyXiangtan UniversityCollege of Computer Science and Electronic Engineering, Hunan UniversityComputer Science and Information Engineering, Providence UniversityXiangtan UniversityHunan Provincial Key Laboratory of Network Investigational Technology, Hunan Police AcademySchool of Economics and Management, Changsha University of Science and TechnologyPersonalised recommendation is a difficult problem that has received a lot of attention to academia and industry. Because of the sparse user–item interaction, cold-start recommendation has been a particularly difficult problem. Some efforts have been made to solve the cold-start problem by using model-agnostic meta-learning on the level of the model and heterogeneous information networks on the level of data. Moreover, using the memory-augmented meta-optimisation method effectively prevents the meta-learning model from entering the local optimum. As a result, this paper proposed memory-augmented meta-learning on meta-path, a new meta-learning method that addresses the cold-start recommendation on the meta-path furthered. The meta-path builds at the data level to enrich the relevant semantic information of the data. To achieve fast adaptation, semantic-specific memory is utilised to conduct the model with semantic parameter initialisation, and the method is optimised by a meta-optimisation method. We put this method to the test using two widely used recommended data set and three cold-start scenarios. The experimental results demonstrate the efficiency of our proposed method.http://dx.doi.org/10.1080/09540091.2021.1996537cold-start recommendationmemory-augmentedmeta-pathmeta-learning
spellingShingle Tianyuan Li
Xin Su
Wei Liu
Wei Liang
Meng-Yen Hsieh
Zhuhui Chen
XuChong Liu
Hong Zhang
Memory-augmented meta-learning on meta-path for fast adaptation cold-start recommendation
Connection Science
cold-start recommendation
memory-augmented
meta-path
meta-learning
title Memory-augmented meta-learning on meta-path for fast adaptation cold-start recommendation
title_full Memory-augmented meta-learning on meta-path for fast adaptation cold-start recommendation
title_fullStr Memory-augmented meta-learning on meta-path for fast adaptation cold-start recommendation
title_full_unstemmed Memory-augmented meta-learning on meta-path for fast adaptation cold-start recommendation
title_short Memory-augmented meta-learning on meta-path for fast adaptation cold-start recommendation
title_sort memory augmented meta learning on meta path for fast adaptation cold start recommendation
topic cold-start recommendation
memory-augmented
meta-path
meta-learning
url http://dx.doi.org/10.1080/09540091.2021.1996537
work_keys_str_mv AT tianyuanli memoryaugmentedmetalearningonmetapathforfastadaptationcoldstartrecommendation
AT xinsu memoryaugmentedmetalearningonmetapathforfastadaptationcoldstartrecommendation
AT weiliu memoryaugmentedmetalearningonmetapathforfastadaptationcoldstartrecommendation
AT weiliang memoryaugmentedmetalearningonmetapathforfastadaptationcoldstartrecommendation
AT mengyenhsieh memoryaugmentedmetalearningonmetapathforfastadaptationcoldstartrecommendation
AT zhuhuichen memoryaugmentedmetalearningonmetapathforfastadaptationcoldstartrecommendation
AT xuchongliu memoryaugmentedmetalearningonmetapathforfastadaptationcoldstartrecommendation
AT hongzhang memoryaugmentedmetalearningonmetapathforfastadaptationcoldstartrecommendation