Towards locality-aware meta-learning of tail node embeddings on networks

Network embedding is an active research area due to the prevalence of network-structured data. While the state of the art often learns high-quality embedding vectors for high-degree nodes with abundant structural connectivity, the quality of the embedding vectors for low-degree or tail nodes is ofte...

Full description

Saved in:
Bibliographic Details
Main Authors: LIU, Zemin, ZHANG, Wentao, FANG, Yuan, ZHANG, Xinming, HOI, Steven C. H.
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2020
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/5296
https://ink.library.smu.edu.sg/context/sis_research/article/6299/viewcontent/CIKM20_meta_tail2vec.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-6299
record_format dspace
spelling sg-smu-ink.sis_research-62992020-09-24T04:18:32Z Towards locality-aware meta-learning of tail node embeddings on networks LIU, Zemin ZHANG, Wentao FANG, Yuan ZHANG, Xinming HOI, Steven C. H. Network embedding is an active research area due to the prevalence of network-structured data. While the state of the art often learns high-quality embedding vectors for high-degree nodes with abundant structural connectivity, the quality of the embedding vectors for low-degree or tail nodes is often suboptimal due to their limited structural connectivity. While many real-world networks are long-tailed, to date little effort has been devoted to tail node embedding. In this paper, we formulate the goal of learning tail node embeddings as a few-shot regression problem, given the few links on each tail node. In particular, since each node resides in its own local context, we personalize the regression model for each tail node. To reduce overfitting in the personalization, we propose a locality-aware meta-learning framework, called metatail2vec, which learns to learn the regression model for the tail nodes at different localities. Finally, we conduct extensive experiments and demonstrate the promising results of meta-tail2vec. (Supplemental materials including code and data are available at https://github.com/smufang/meta-tail2vec.) 2020-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5296 info:doi/10.1145/3340531.3411910 https://ink.library.smu.edu.sg/context/sis_research/article/6299/viewcontent/CIKM20_meta_tail2vec.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 meta-learning network embedding tail nodes 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 meta-learning
network embedding
tail nodes
Databases and Information Systems
OS and Networks
spellingShingle meta-learning
network embedding
tail nodes
Databases and Information Systems
OS and Networks
LIU, Zemin
ZHANG, Wentao
FANG, Yuan
ZHANG, Xinming
HOI, Steven C. H.
Towards locality-aware meta-learning of tail node embeddings on networks
description Network embedding is an active research area due to the prevalence of network-structured data. While the state of the art often learns high-quality embedding vectors for high-degree nodes with abundant structural connectivity, the quality of the embedding vectors for low-degree or tail nodes is often suboptimal due to their limited structural connectivity. While many real-world networks are long-tailed, to date little effort has been devoted to tail node embedding. In this paper, we formulate the goal of learning tail node embeddings as a few-shot regression problem, given the few links on each tail node. In particular, since each node resides in its own local context, we personalize the regression model for each tail node. To reduce overfitting in the personalization, we propose a locality-aware meta-learning framework, called metatail2vec, which learns to learn the regression model for the tail nodes at different localities. Finally, we conduct extensive experiments and demonstrate the promising results of meta-tail2vec. (Supplemental materials including code and data are available at https://github.com/smufang/meta-tail2vec.)
format text
author LIU, Zemin
ZHANG, Wentao
FANG, Yuan
ZHANG, Xinming
HOI, Steven C. H.
author_facet LIU, Zemin
ZHANG, Wentao
FANG, Yuan
ZHANG, Xinming
HOI, Steven C. H.
author_sort LIU, Zemin
title Towards locality-aware meta-learning of tail node embeddings on networks
title_short Towards locality-aware meta-learning of tail node embeddings on networks
title_full Towards locality-aware meta-learning of tail node embeddings on networks
title_fullStr Towards locality-aware meta-learning of tail node embeddings on networks
title_full_unstemmed Towards locality-aware meta-learning of tail node embeddings on networks
title_sort towards locality-aware meta-learning of tail node embeddings on networks
publisher Institutional Knowledge at Singapore Management University
publishDate 2020
url https://ink.library.smu.edu.sg/sis_research/5296
https://ink.library.smu.edu.sg/context/sis_research/article/6299/viewcontent/CIKM20_meta_tail2vec.pdf
_version_ 1770575374451736576