Regularized online tensor factorization for sparse knowledge graph embeddings

Author:

Zulaika UnaiORCID,Almeida Aitor,López-de-Ipiña Diego

Abstract

AbstractKnowledge Graphs represent real-world facts and are used in several applications; however, they are often incomplete and have many missing facts. Link prediction is the task of completing these missing facts from existing ones. Embedding models based on Tensor Factorization attain state-of-the-art results in link prediction. Nevertheless, the embeddings they produce can not be easily interpreted. Inspired by previous work on word embeddings, we propose inducing sparsity in the bilinear tensor factorization model, RESCAL, to build interpretable Knowledge Graph embeddings. To overcome the difficulties that stochastic gradient descent has when producing sparse solutions, we add $$l_1$$ l 1 regularization to the learning objective by using the generalized Regularized Dual Averaging online optimization algorithm. The proposed method substantially improves the interpretability of the learned embeddings while maintaining competitive performance in the standard metrics.

Funder

Eusko Jaurlaritza

Ministerio de Economía y Competitividad

Ministerio de Ciencia, Innovación y Universidades

Universidad de Deusto

Publisher

Springer Science and Business Media LLC

Subject

Artificial Intelligence,Software

Reference46 articles.

1. Allen C, Balazevic I, Hospedales T (2021) Interpreting knowledge graph relation representation from word embeddings. In: International conference on learning representations, https://openreview.net/forum?id=gLWj29369lW

2. Balazevic I, Allen C, Hospedales T (2019) TuckER: tensor factorization for knowledge graph completion. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, pp. 5185–5194, https://doi.org/10.18653/v1/D19-1522 https://aclanthology.org/D19-1522

3. Barbieri N, Bonchi F, Manco G (2014) Who to follow and why: link prediction with explanations. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 1266–1275

4. Bordes A, Usunier N, Garcia-Duran A, et al (2013) Translating embeddings for modeling multi-relational data. In: Burges C, Bottou L, Welling M, et al (eds) Advances in neural information processing systems, vol 26. Curran Associates, Inc., https://proceedings.neurips.cc/paper/2013/file/1cecc7a77928ca8133fa24680a88d2f9-Paper.pdf

5. Chandrahas , Sengupta T, Pragadeesh C, et al (2020) Inducing interpretability in knowledge graph embeddings. In: Proceedings of the 17th international conference on natural language processing (ICON). NLP Association of India (NLPAI), Indian Institute of Technology Patna, Patna, India, pp. 70–75, https://aclanthology.org/2020.icon-main.9

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3