EsiNet: Enhanced network representation via further learning the semantic information of edges

Anqing Zheng, Chong Feng*, Fang Yang, Huanhuan Zhang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Network representation learning (NRL) is a crucial method to learn low-dimensional vertex representations to capture network information. However, conventional NRL models only regard each edge as a binary or continuous value while neglecting the rich semantic information on edges. To enhance network representation for Social Relation Extraction (SRE) task, we present a novel deep neural network based model, EsiNet, by learning the structure and semantic information of edges simultaneously. Compared with previous work, EsiNet focuses on further learning the interactions between vertices and capturing the correlations between labels. By jointly optimizing the objective function of these two components, EsiNet can preserve both the semantic and structural information of edges. Extensive experiments on several public datasets demonstrate that EsiNet outperforms other baselines significantly, by around 3% to 5% on hits@10 absolutely.

Original languageEnglish
Title of host publicationProceedings - IEEE 31st International Conference on Tools with Artificial Intelligence, ICTAI 2019
PublisherIEEE Computer Society
Pages1011-1018
Number of pages8
ISBN (Electronic)9781728137988
DOIs
Publication statusPublished - Nov 2019
Event31st IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2019 - Portland, United States
Duration: 4 Nov 20196 Nov 2019

Publication series

NameProceedings - International Conference on Tools with Artificial Intelligence, ICTAI
Volume2019-November
ISSN (Print)1082-3409

Conference

Conference31st IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2019
Country/TerritoryUnited States
CityPortland
Period4/11/196/11/19

Keywords

  • Multi-label classification
  • Network representation learning
  • Social relation extraction

Fingerprint

Dive into the research topics of 'EsiNet: Enhanced network representation via further learning the semantic information of edges'. Together they form a unique fingerprint.

Cite this