Document Type

Conference Paper

Department/Unit

Department of Computer Science

Title

A structural representation learning for multi-relational networks

Language

English

Abstract

Most of the existing multi-relational network embedding methods, e.g., TransE, are formulated to preserve pair-wise connectivity structures in the networks. With the observations that significant triangular connectivity structures and parallelogram connectivity structures found in many real multi-relational networks are often ignored and that a hard-constraint commonly adopted by most of the network embedding methods is inaccurate by design, we propose a novel representation learning model for multi-relational networks which can alleviate both fundamental limitations. Scalable learning algorithms are derived using the stochastic gradient descent algorithm and negative sampling. Extensive experiments on real multi-relational network datasets of WordNet and Freebase demonstrate the efficacy of the proposed model when compared with the state-of-the-art embedding methods.

Keywords

Natural Language Processing, Information Extraction, Information Retrieval, Machine Learning, Multi-instance/Multi-label/Multi-view learning, Knowledge-based Learning

Publication Date

8-2017

Source Publication Title

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence

Start Page

4047

End Page

4053

Conference Location

Melbourne, Australia

Publisher

International Joint Conferences on Artificial Intelligence

Copyright

Copyright © 2017 International Joint Conferences on Artificial Intelligence All rights reserved. No part of this book may be reproduced in any form by any electronic or mechanical means (including photocopying, recording, or information storage and retrieval) without permission in writing from the publisher.

Funder

This work has been partially supported by NSFC under Grant No. 61300178, National Program on Key Basic Research Project under Grant No. 2013CB329605.

Link to Publisher's Edition

https://www.ijcai.org/proceedings/2017/0565.pdf

ISBN (print)

9780999241103

This document is currently not available here.

Share

COinS