Meta-learning on heterogeneous information networks for cold-start recommendation
Cold-start recommendation has been a challenging problem due to sparse user-item interactions for new users or items. Existing efforts have alleviated the cold-start issue to some extent, most of which approach the problem at the data level. Earlier methods often incorporate auxiliary data as user o...
Saved in:
Main Authors: | , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2020
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/5155 https://ink.library.smu.edu.sg/context/sis_research/article/6158/viewcontent/KDD20_MetaHIN.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-6158 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-61582021-05-24T02:33:54Z Meta-learning on heterogeneous information networks for cold-start recommendation LU, Yuanfu FANG, Yuan SHI, Chuan Cold-start recommendation has been a challenging problem due to sparse user-item interactions for new users or items. Existing efforts have alleviated the cold-start issue to some extent, most of which approach the problem at the data level. Earlier methods often incorporate auxiliary data as user or item features, while more recent methods leverage heterogeneous information networks (HIN) to capture richer semantics via higher-order graph structures. On the other hand, recent meta-learning paradigm sheds light on addressing cold-start recommendation at the model level, given its ability to rapidly adapt to new tasks with scarce labeled data, or in the context of cold-start recommendation, new users and items with very few interactions. Thus, we are inspired to develop a novel meta-learning approach named MetaHIN to address cold-start recommendation on HINs, to exploit the power of meta-learning at the model level and HINs at the data level simultaneously. The solution is non-trivial, for how to capture HIN-based semantics in the metalearning setting, and how to learn the general knowledge that can be easily adapted to multifaceted semantics, remain open questions. In MetaHIN, we propose a novel semantic-enhanced tasks constructor and a co-adaptation meta-learner to address the two questions. Extensive experiments demonstrate that MetaHIN significantly outperforms the state of the arts in various cold-start scenarios. (Code and dataset are available at https://github.com/rootlu/MetaHIN.) 2020-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5155 info:doi/10.1145/3394486.3403207 https://ink.library.smu.edu.sg/context/sis_research/article/6158/viewcontent/KDD20_MetaHIN.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Heterogeneous Information Network Meta-learning Cold-start Recommendation Databases and Information Systems OS and Networks |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Heterogeneous Information Network Meta-learning Cold-start Recommendation Databases and Information Systems OS and Networks |
spellingShingle |
Heterogeneous Information Network Meta-learning Cold-start Recommendation Databases and Information Systems OS and Networks LU, Yuanfu FANG, Yuan SHI, Chuan Meta-learning on heterogeneous information networks for cold-start recommendation |
description |
Cold-start recommendation has been a challenging problem due to sparse user-item interactions for new users or items. Existing efforts have alleviated the cold-start issue to some extent, most of which approach the problem at the data level. Earlier methods often incorporate auxiliary data as user or item features, while more recent methods leverage heterogeneous information networks (HIN) to capture richer semantics via higher-order graph structures. On the other hand, recent meta-learning paradigm sheds light on addressing cold-start recommendation at the model level, given its ability to rapidly adapt to new tasks with scarce labeled data, or in the context of cold-start recommendation, new users and items with very few interactions. Thus, we are inspired to develop a novel meta-learning approach named MetaHIN to address cold-start recommendation on HINs, to exploit the power of meta-learning at the model level and HINs at the data level simultaneously. The solution is non-trivial, for how to capture HIN-based semantics in the metalearning setting, and how to learn the general knowledge that can be easily adapted to multifaceted semantics, remain open questions. In MetaHIN, we propose a novel semantic-enhanced tasks constructor and a co-adaptation meta-learner to address the two questions. Extensive experiments demonstrate that MetaHIN significantly outperforms the state of the arts in various cold-start scenarios. (Code and dataset are available at https://github.com/rootlu/MetaHIN.) |
format |
text |
author |
LU, Yuanfu FANG, Yuan SHI, Chuan |
author_facet |
LU, Yuanfu FANG, Yuan SHI, Chuan |
author_sort |
LU, Yuanfu |
title |
Meta-learning on heterogeneous information networks for cold-start recommendation |
title_short |
Meta-learning on heterogeneous information networks for cold-start recommendation |
title_full |
Meta-learning on heterogeneous information networks for cold-start recommendation |
title_fullStr |
Meta-learning on heterogeneous information networks for cold-start recommendation |
title_full_unstemmed |
Meta-learning on heterogeneous information networks for cold-start recommendation |
title_sort |
meta-learning on heterogeneous information networks for cold-start recommendation |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2020 |
url |
https://ink.library.smu.edu.sg/sis_research/5155 https://ink.library.smu.edu.sg/context/sis_research/article/6158/viewcontent/KDD20_MetaHIN.pdf |
_version_ |
1770575297680244736 |