Department of Computer Science
A structural representation learning for multi-relational networks
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.
Natural Language Processing, Information Extraction, Information Retrieval, Machine Learning, Multi-instance/Multi-label/Multi-view learning, Knowledge-based Learning
Source Publication Title
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
International Joint Conferences on Artificial Intelligence
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.
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
Liu, L., Li, X., Cheung, W., & Xu, C. (2017). A structural representation learning for multi-relational networks. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 4047-4053. Retrieved from https://repository.hkbu.edu.hk/hkbu_staff_publication/6536