CO2Vec: Embeddings of co-ordered networks based on mutual reinforcement

We study the problem of representation learning for multiple types of entities in a co-ordered network where order relations exist among entities of the same type, and association relations exist across entities of different types. The key challenge in learning co-ordered network embedding is to pre...

Full description

Saved in:
Bibliographic Details
Main Authors: CHIANG, Meng-Fen, LIM, Ee-Peng, LEE, Wang-Chien, PRASETYO, Philips Kokoh
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2020
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/5941
https://ink.library.smu.edu.sg/context/sis_research/article/6944/viewcontent/2020_DSAA_CO2Vec_Embeddings_of_Co_Ordered_Networks_Based_on_Mutual_Reinforcement.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-6944
record_format dspace
spelling sg-smu-ink.sis_research-69442021-05-17T08:02:26Z CO2Vec: Embeddings of co-ordered networks based on mutual reinforcement CHIANG, Meng-Fen LIM, Ee-Peng LEE, Wang-Chien PRASETYO, Philips Kokoh We study the problem of representation learning for multiple types of entities in a co-ordered network where order relations exist among entities of the same type, and association relations exist across entities of different types. The key challenge in learning co-ordered network embedding is to preserve order relations among entities of the same type while leveraging on the general consistency in order relations between different entity types. In this paper, we propose an embedding model, CO2Vec, that addresses this challenge using mutually reinforced order dependencies. Specifically, CO2Vec explores in-direct order dependencies as supplementary evidence to enhance order representation learning across different types of entities. We conduct extensive experiments on both synthetic and real world datasets to demonstrate the robustness and effectiveness of CO2Vec against several strong baselines in link prediction task. We also design a comprehensive evaluation framework to study the performance of CO2Vec under different settings. In particular, our results show the robustness of CO2Vec with the removal of order relations from the original networks. 2020-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5941 info:doi/10.1109/DSAA49011.2020.00027 https://ink.library.smu.edu.sg/context/sis_research/article/6944/viewcontent/2020_DSAA_CO2Vec_Embeddings_of_Co_Ordered_Networks_Based_on_Mutual_Reinforcement.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 Semantics Task analysis Support vector machines Robustness Machine learning Uncertainty Head Databases and Information Systems Numerical Analysis and Scientific Computing
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Semantics
Task analysis
Support vector machines
Robustness
Machine learning
Uncertainty
Head
Databases and Information Systems
Numerical Analysis and Scientific Computing
spellingShingle Semantics
Task analysis
Support vector machines
Robustness
Machine learning
Uncertainty
Head
Databases and Information Systems
Numerical Analysis and Scientific Computing
CHIANG, Meng-Fen
LIM, Ee-Peng
LEE, Wang-Chien
PRASETYO, Philips Kokoh
CO2Vec: Embeddings of co-ordered networks based on mutual reinforcement
description We study the problem of representation learning for multiple types of entities in a co-ordered network where order relations exist among entities of the same type, and association relations exist across entities of different types. The key challenge in learning co-ordered network embedding is to preserve order relations among entities of the same type while leveraging on the general consistency in order relations between different entity types. In this paper, we propose an embedding model, CO2Vec, that addresses this challenge using mutually reinforced order dependencies. Specifically, CO2Vec explores in-direct order dependencies as supplementary evidence to enhance order representation learning across different types of entities. We conduct extensive experiments on both synthetic and real world datasets to demonstrate the robustness and effectiveness of CO2Vec against several strong baselines in link prediction task. We also design a comprehensive evaluation framework to study the performance of CO2Vec under different settings. In particular, our results show the robustness of CO2Vec with the removal of order relations from the original networks.
format text
author CHIANG, Meng-Fen
LIM, Ee-Peng
LEE, Wang-Chien
PRASETYO, Philips Kokoh
author_facet CHIANG, Meng-Fen
LIM, Ee-Peng
LEE, Wang-Chien
PRASETYO, Philips Kokoh
author_sort CHIANG, Meng-Fen
title CO2Vec: Embeddings of co-ordered networks based on mutual reinforcement
title_short CO2Vec: Embeddings of co-ordered networks based on mutual reinforcement
title_full CO2Vec: Embeddings of co-ordered networks based on mutual reinforcement
title_fullStr CO2Vec: Embeddings of co-ordered networks based on mutual reinforcement
title_full_unstemmed CO2Vec: Embeddings of co-ordered networks based on mutual reinforcement
title_sort co2vec: embeddings of co-ordered networks based on mutual reinforcement
publisher Institutional Knowledge at Singapore Management University
publishDate 2020
url https://ink.library.smu.edu.sg/sis_research/5941
https://ink.library.smu.edu.sg/context/sis_research/article/6944/viewcontent/2020_DSAA_CO2Vec_Embeddings_of_Co_Ordered_Networks_Based_on_Mutual_Reinforcement.pdf
_version_ 1770575699565871104