mSHINE : a multiple-meta-paths simultaneous learning framework for heterogeneous information network embedding
Heterogeneous information networks (HINs) become popular in recent years for its strong capability of modelling objects with abundant information using explicit network structure. Network embedding has been proved as an effective method to convert information networks into lower-dimensional space, w...
Saved in:
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/153697 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-153697 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1536972021-12-08T08:17:23Z mSHINE : a multiple-meta-paths simultaneous learning framework for heterogeneous information network embedding Zhang, Xinyi Chen, Lihui School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Heterogeneous Information Network Network Embedding Heterogeneous information networks (HINs) become popular in recent years for its strong capability of modelling objects with abundant information using explicit network structure. Network embedding has been proved as an effective method to convert information networks into lower-dimensional space, whereas the core information can be well preserved. However, traditional network embedding algorithms are sub-optimal in capturing rich while potentially incompatible semantics provided by HINs. To address this issue, a novel meta-path-based HIN representation learning framework named mSHINE is designed to simultaneously learn multiple node representations for different meta-paths. More specifically, one representation learning module inspired by the RNN structure is developed and multiple node representations can be learned simultaneously, where each representation is associated with one respective meta-path. By measuring the relevance between nodes with the designed objective function, the learned module can be applied in downstream link prediction tasks. A set of criteria for selecting initial meta-paths is proposed as the other module in mSHINE which is important to reduce the optimal meta-path selection cost when no prior knowledge of suitable meta-paths is available. To corroborate the effectiveness of mSHINE, extensive experimental studies including node classification and link prediction are conducted on five real-world datasets. The results demonstrate that mSHINE outperforms other state-of-the-art HIN embedding methods. Accepted version 2021-12-08T08:17:23Z 2021-12-08T08:17:23Z 2020 Journal Article Zhang, X. & Chen, L. (2020). mSHINE : a multiple-meta-paths simultaneous learning framework for heterogeneous information network embedding. IEEE Transactions On Knowledge and Data Engineering. https://dx.doi.org/10.1109/TKDE.2020.3025464 1041-4347 https://hdl.handle.net/10356/153697 10.1109/TKDE.2020.3025464 en IEEE Transactions on Knowledge and Data Engineering © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TKDE.2020.3025464. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering Heterogeneous Information Network Network Embedding |
spellingShingle |
Engineering::Electrical and electronic engineering Heterogeneous Information Network Network Embedding Zhang, Xinyi Chen, Lihui mSHINE : a multiple-meta-paths simultaneous learning framework for heterogeneous information network embedding |
description |
Heterogeneous information networks (HINs) become popular in recent years for its strong capability of modelling objects with abundant information using explicit network structure. Network embedding has been proved as an effective method to convert information networks into lower-dimensional space, whereas the core information can be well preserved. However, traditional network embedding algorithms are sub-optimal in capturing rich while potentially incompatible semantics provided by HINs. To address this issue, a novel meta-path-based HIN representation learning framework named mSHINE is designed to simultaneously learn multiple node representations for different meta-paths. More specifically, one representation learning module inspired by the RNN structure is developed and multiple node representations can be learned simultaneously, where each representation is associated with one respective meta-path. By measuring the relevance between nodes with the designed objective function, the learned module can be applied in downstream link prediction tasks. A set of criteria for selecting initial meta-paths is proposed as the other module in mSHINE which is important to reduce the optimal meta-path selection cost when no prior knowledge of suitable meta-paths is available. To corroborate the effectiveness of mSHINE, extensive experimental studies including node classification and link prediction are conducted on five real-world datasets. The results demonstrate that mSHINE outperforms other state-of-the-art HIN embedding methods. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Zhang, Xinyi Chen, Lihui |
format |
Article |
author |
Zhang, Xinyi Chen, Lihui |
author_sort |
Zhang, Xinyi |
title |
mSHINE : a multiple-meta-paths simultaneous learning framework for heterogeneous information network embedding |
title_short |
mSHINE : a multiple-meta-paths simultaneous learning framework for heterogeneous information network embedding |
title_full |
mSHINE : a multiple-meta-paths simultaneous learning framework for heterogeneous information network embedding |
title_fullStr |
mSHINE : a multiple-meta-paths simultaneous learning framework for heterogeneous information network embedding |
title_full_unstemmed |
mSHINE : a multiple-meta-paths simultaneous learning framework for heterogeneous information network embedding |
title_sort |
mshine : a multiple-meta-paths simultaneous learning framework for heterogeneous information network embedding |
publishDate |
2021 |
url |
https://hdl.handle.net/10356/153697 |
_version_ |
1718928699524382720 |