research-article

ActiveLink: Deep Active Learning for Link Prediction in Knowledge Graphs

Authors:

Natalia Ostapuk,

Philippe Cudre-MaurouxAuthors Info & Claims

WWW '19: The World Wide Web Conference

Pages 1398 - 1408

https://doi.org/10.1145/3308558.3313620

Published: 13 May 2019 Publication History

Abstract

Neural networks have recently been shown to be highly effective at predicting links for constructing knowledge graphs. Existing research has mainly focused on designing 1) deep neural network models that are expressive in capturing fine-grained semantics, e.g., NTN and ConvE, but that are however less scalable; or 2) shallow models that are scalable, e.g., TransE and DistMult, yet limited in capturing expressive semantic features. In this work, we demonstrate that we can get the best of both worlds while drastically reducing the amount of data needed to train a deep network by leveraging active learning.

We present a novel deep active learning framework, ActiveLink, which can be applied to actively train any neural link predictor. Inspired by recent advances in Bayesian deep learning, ActiveLink takes a Bayesian view on neural link predictors, thereby enabling uncertainty sampling for deep active learning. ActiveLink extends uncertainty sampling by exploiting the underlying structure of the knowledge graph, i.e., links between entities, to improve sampling effectiveness. To accelerate model training, ActiveLink further adopts an incremental training method that allows deep neural networks to be incrementally trained while optimizing their generalizability at each iteration. Extensive validation on real-world datasets shows that ActiveLink is able to match state-of-the-art approaches while requiring only 20% of the original training data.

References

[1]

Sungjin Ahn, Anoop Korattikara, and Max Welling. 2012. Bayesian posterior sampling via stochastic gradient fisher scoring. arXiv preprint arXiv:1206.6380(2012).

Digital Library

[2]

Marcin Andrychowicz, Misha Denil, Sergio Gomez, Matthew W Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, and Nando De Freitas. 2016. Learning to learn by gradient descent by gradient descent. In Advances in Neural Information Processing Systems (NIPS). 3981-3989.

Digital Library

[3]

Vincent D Blondel, Jean-Loup Guillaume, Renaud Lambiotte, and Etienne Lefebvre. 2008. Fast unfolding of communities in large networks. Journal of Statistical Mechanics: Theory and Experiment2008, 10(2008), P10008.

[4]

Antoine Bordes, Xavier Glorot, Jason Weston, and Yoshua Bengio. 2014. A semantic matching energy function for learning with multi-relational data. Machine Learning94, 2 (2014), 233-259.

Digital Library

[5]

Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In Advances in Neural Information Processing Systems (NIPS). 2787-2795.

Digital Library

[6]

Lijun Chang, Wei Li, Lu Qin, Wenjie Zhang, and Shiyu Yang. 2017. : Fast and Exact Structural Graph Clustering. IEEE Transactions on Knowledge and Data Engineering (TKDE)29, 2(2017), 387-401.

Digital Library

[7]

David A Cohn, Zoubin Ghahramani, and Michael I Jordan. 1996. Active Learning with Statistical Models. Journal of Artificial Intelligence Research (JAIR) (1996).

Digital Library

[8]

Tim Dettmers, Pasquale Minervini, Pontus Stenetorp, and Sebastian Riedel. 2018. Convolutional 2d knowledge graph embeddings. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI). AAAI, 1811-1818.

[9]

Xin Dong, Evgeniy Gabrilovich, Geremy Heitz, Wilko Horn, Ni Lao, Kevin Murphy, Thomas Strohmann, Shaohua Sun, and Wei Zhang. 2014. Knowledge vault: A web-scale approach to probabilistic knowledge fusion. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). ACM, 601-610.

Digital Library

[10]

Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. arXiv preprint arXiv:1703.03400(2017).

Digital Library

[11]

Linton C Freeman. 1965. Elementary applied statistics: for students in behavioral science. John Wiley & Sons.

[12]

Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. In Proceedings of the 33rd International Conference on Machine Learning (ICML). 1050-1059.

Digital Library

[13]

Yarin Gal, Riashat Islam, and Zoubin Ghahramani. 2017. Deep bayesian active learning with image data. Proceedings of the 34th International Conference on Machine Learning (ICML), 1183-1192.

Digital Library

[14]

Geoffrey E Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, and Ruslan R Salakhutdinov. 2012. Improving Neural Networks by Preventing Co-adaptation of Feature Detectors. arXiv preprint arXiv:1207.0580(2012).

[15]

Neil Houlsby, Ferenc Huszár, Zoubin Ghahramani, and Máte´ Lengyel. 2011. Bayesian active learning for classification and preference learning. arXiv preprint arXiv:1112.5745(2011).

[16]

Alex Kendall and Yarin Gal. 2017. What uncertainties do we need in bayesian deep learning for computer vision?. In Advances in Neural Information Processing Systems (NIPS). 5580-5590.

Digital Library

[17]

Andreas Krause, Ajit Singh, and Carlos Guestrin. 2008. Near-optimal Sensor Placements in Gaussian Processes: Theory, Efficient Algorithms and Empirical Studies. Journal of Machine Learning Research (JMLR)9, Feb (2008), 235-284.

Digital Library

[18]

Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (NIPS). 1097-1105.

Digital Library

[19]

Ni Lao, Tom Mitchell, and William W Cohen. 2011. Random walk inference and learning in a large scale knowledge base. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, 529-539.

Digital Library

[20]

David D Lewis and William A Gale. 1994. A Sequential Algorithm for Training Text Classifiers. In Proceedings of the 17th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR). ACM, 3-12.

Digital Library

[21]

Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, and Xuan Zhu. 2015. Learning entity and relation embeddings for knowledge graph completion. In Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI). AAAI, 2181-2187.

Digital Library

[22]

Maximilian Nickel, Kevin Murphy, Volker Tresp, and Evgeniy Gabrilovich. 2016. A review of relational machine learning for knowledge graphs. Proc. IEEE104, 1 (2016), 11-33.

[23]

Maximilian Nickel, Lorenzo Rosasco, Tomaso A Poggio, 2016. Holographic Embeddings of Knowledge Graphs. In Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI). AAAI, 1955-1961.

Digital Library

[24]

Maximilian Nickel, Volker Tresp, and Hans-Peter Kriegel. 2011. A Three-Way Model for Collective Learning on Multi-Relational Data. In Proceedings of the 28th International Conference on Machine Learning (ICML), Vol. 11. 809-816.

Digital Library

[25]

Maximilian Nickel, Volker Tresp, and Hans-Peter Kriegel. 2012. Factorizing yago: scalable machine learning for linked data. In Proceedings of the 21st International Conference on World Wide Web (WWW). ACM, 271-280.

Digital Library

[26]

Nicholas Roy and Andrew McCallum. 2001. Toward Optimal Active Learning Through Monte Carlo Estimation of Error Reduction. Proceedings of the 18th International Conference on Machine Learning (ICML) (2001), 441-448.

Digital Library

[27]

Burr Settles. 2010. Active Learning Literature Survey. University of Wisconsin, Madison52, 55-66 (2010), 11.

Digital Library

[28]

Claude Elwood Shannon. 2001. A mathematical theory of communication. ACM SIGMOBILE Mobile Computing and Communications Review5, 1(2001), 3-55.

Digital Library

[29]

Yanyao Shen, Hyokun Yun, Zachary C Lipton, Yakov Kronrod, and Animashree Anandkumar. 2017. Deep Active Learning for Named Entity Recognition. arXiv preprint arXiv:1707.05928(2017).

[30]

Richard Socher, Danqi Chen, Christopher D Manning, and Andrew Ng. 2013. Reasoning with neural tensor networks for knowledge base completion. In Advances in Neural Information Processing Systems (NIPS). 926-934.

Digital Library

[31]

Nitish Srivastava, Geoffrey E Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a Simple Way to Prevent Neural Networks from Overfitting.Journal of Machine Learning Research (JMLR)15, 1 (2014), 1929-1958.

Digital Library

[32]

Kristina Toutanova, Danqi Chen, Patrick Pantel, Hoifung Poon, Pallavi Choudhury, and Michael Gamon. 2015. Representing text for joint embedding of text and knowledge bases. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP). 1499-1509.

[33]

The´o Trouillon, Johannes Welbl, Sebastian Riedel, E&Acute;ric Gaussier, and Guillaume Bouchard. 2016. Complex embeddings for simple link prediction. In Proceedings of the 33rd International Conference on Machine Learning (ICML). 2071-2080.

Digital Library

[34]

Keze Wang, Dongyu Zhang, Ya Li, Ruimao Zhang, and Liang Lin. 2016. Cost-effective active learning for deep image classification. IEEE Transactions on Circuits and Systems for Video Technology (2016).

Digital Library

[35]

Quan Wang, Zhendong Mao, Bin Wang, and Li Guo. 2017. Knowledge graph embedding: A survey of approaches and applications. IEEE Transactions on Knowledge and Data Engineering (TKDE)29, 12(2017), 2724-2743.

[36]

Zhen Wang, Jianwen Zhang, Jianlin Feng, and Zheng Chen. 2014. Knowledge Graph Embedding by Translating on Hyperplanes. In Proceedings of the 28th AAAI Conference on Artificial Intelligence (AAAI), Vol. 14. AAAI, 1112-1119.

Digital Library

[37]

Max Welling and Yee W Teh. 2011. Bayesian Learning via Sochastic Gradient Langevin Dynamics. In Proceedings of the 28th International Conference on Machine Learning (ICML). 681-688.

Digital Library

[38]

Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2015. Embedding entities and relations for learning and inference in knowledge bases. In Proceedings of the 3rd International Conference on Learning Representations (ICLR).

[39]

Jie Yang, Thomas Drake, Andreas Damianou, and Yoelle Maarek. 2018. Leveraging crowdsourcing data for deep active learning - an application: Learning intents in Alexa. In Proceedings of the 2018 edition of The Web Conference (WWW). ACM, 23-32.

Digital Library

[40]

Ye Zhang, Matthew Lease, and Byron C Wallace. 2017. Active Discriminative Text Representation Learning. In Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI). AAAI, 3386-3392.

Digital Library

Cited By

Yu WYang JYang DChua TNgo CKa-Wei Lee RKumar RLauw H(2024)Robust Link Prediction over Noisy Hyper-Relational Knowledge Graphs via Active LearningProceedings of the ACM Web Conference 202410.1145/3589334.3645686(2282-2293)Online publication date: 13-May-2024
https://dl.acm.org/doi/10.1145/3589334.3645686
Mourtzis DWang L(2024)Industry 5.0: perspectives, concepts, and technologiesManufacturing from Industry 4.0 to Industry 5.010.1016/B978-0-443-13924-6.00003-X(63-96)Online publication date: 2024
https://doi.org/10.1016/B978-0-443-13924-6.00003-X
Meduri VQuamar ALei CQin XReinwald B(2024)Alfa: active learning for graph neural network-based semantic schema alignmentThe VLDB Journal — The International Journal on Very Large Data Bases10.1007/s00778-023-00822-z33:4(981-1011)Online publication date: 1-Jul-2024
https://dl.acm.org/doi/10.1007/s00778-023-00822-z
Show More Cited By

Recommendations

Stock prediction using deep learning

Stock market is considered chaotic, complex, volatile and dynamic. Undoubtedly, its prediction is one of the most challenging tasks in time series forecasting. Moreover existing Artificial Neural Network (ANN) approaches fail to provide encouraging ...
Deep learning: an overview and main paradigms

In the present paper, we examine and analyze main paradigms of learning of multilayer neural networks starting with a single layer perceptron and ending with deep neural networks, which are considered regarded as a breakthrough in the field of the ...
Neighborhood Aggregation Embedding Model for Link Prediction in Knowledge Graphs
Web Engineering
Abstract
Link prediction has become a hot topic of knowledge graphs (KGs) in recent years. It aims at predicting missing links between entities to complement KGs. The most successful methods for this problem are embedding-based. Most previous works only ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

WWW '19: The World Wide Web Conference

May 2019

3620 pages

ISBN:9781450366748

DOI:10.1145/3308558

Editors:
Ling Liu
Georgia Tech, USA
,
Ryen White
Microsoft Research, USA

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

IW3C2: International World Wide Web Conference Committee

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 13 May 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

WWW '19

WWW '19: The Web Conference

May 13 - 17, 2019

CA, San Francisco, USA

Acceptance Rates

Overall Acceptance Rate 1,899 of 8,196 submissions, 23%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

28
Total Citations
View Citations
1,120
Total Downloads

Downloads (Last 12 months)94
Downloads (Last 6 weeks)6

Reflects downloads up to 18 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Yu WYang JYang DChua TNgo CKa-Wei Lee RKumar RLauw H(2024)Robust Link Prediction over Noisy Hyper-Relational Knowledge Graphs via Active LearningProceedings of the ACM Web Conference 202410.1145/3589334.3645686(2282-2293)Online publication date: 13-May-2024
https://dl.acm.org/doi/10.1145/3589334.3645686
Mourtzis DWang L(2024)Industry 5.0: perspectives, concepts, and technologiesManufacturing from Industry 4.0 to Industry 5.010.1016/B978-0-443-13924-6.00003-X(63-96)Online publication date: 2024
https://doi.org/10.1016/B978-0-443-13924-6.00003-X
Meduri VQuamar ALei CQin XReinwald B(2024)Alfa: active learning for graph neural network-based semantic schema alignmentThe VLDB Journal — The International Journal on Very Large Data Bases10.1007/s00778-023-00822-z33:4(981-1011)Online publication date: 1-Jul-2024
https://dl.acm.org/doi/10.1007/s00778-023-00822-z
Hwang SLee SKim HOh MOk JKwak SOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Active learning for semantic segmentation with multi-class label queryProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3667297(27020-27039)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3667297
Drien OFreiman MAmarilli AAmsterdamer Y(2023)Query-Guided Resolution in Uncertain DatabasesProceedings of the ACM on Management of Data10.1145/35893251:2(1-27)Online publication date: 20-Jun-2023
https://doi.org/10.1145/3589325
Duan CJia TCai HLi YHuang G(2023)AFALog: A General Augmentation Framework for Log-based Anomaly Detection with Active Learning2023 IEEE 34th International Symposium on Software Reliability Engineering (ISSRE)10.1109/ISSRE59848.2023.00068(46-56)Online publication date: 9-Oct-2023
https://doi.org/10.1109/ISSRE59848.2023.00068
Duan CJia TLi YHuang G(2023)AcLog: An Approach to Detecting Anomalies from System Logs with Active Learning2023 IEEE International Conference on Web Services (ICWS)10.1109/ICWS60048.2023.00062(436-443)Online publication date: Jul-2023
https://doi.org/10.1109/ICWS60048.2023.00062
You XZhang LWang JBao ZWu YDong S(2023)ENLD: Efficient Noisy Label Detection for Incremental Datasets in Data Lake2023 IEEE 39th International Conference on Data Engineering (ICDE)10.1109/ICDE55515.2023.00151(1940-1952)Online publication date: Apr-2023
https://doi.org/10.1109/ICDE55515.2023.00151
Zhan QLiu GXie XZhang MSun G(2023)Bio-inspired Active Learning method in spiking neural networkKnowledge-Based Systems10.1016/j.knosys.2022.110193261:COnline publication date: 15-Feb-2023
https://dl.acm.org/doi/10.1016/j.knosys.2022.110193
Hayes NMerkurjev EWei G(2023)Integrating transformer and autoencoder techniques with spectral graph algorithms for the prediction of scarcely labeled molecular dataComputers in Biology and Medicine10.1016/j.compbiomed.2022.106479153(106479)Online publication date: Feb-2023
https://doi.org/10.1016/j.compbiomed.2022.106479
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents