Abstract
In this work, we propose a novel framework for labeling entity alignments in knowledge graph datasets. Different strategies to select informative instances for the human labeler build the core of our framework. We illustrate how the labeling of entity alignments is different from assigning class labels to single instances and how these differences affect the labeling efficiency. Based on these considerations, we propose and evaluate different active and passive learning strategies. One of our main findings is that passive learning approaches, which can be efficiently precomputed, and deployed more easily, achieve performance comparable to the active learning strategies. In the spirit of reproducible research, we make our code available at https://github.com/mberr/ea_active_learning.
M. Berrendorf and E. Faerman—equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Note that the frequently used DBP15k dataset is not suitable for our experiments due to its construction. Exclusive nodes in DBP15K are exactly those having a degree of one and are therefore trivial to identify.
References
Bast, H., Björn, B., Haussmann, E.: Semantic search on text and knowledge bases. Found. Trends Inf. Retrieval 10(2–3), 119–271 (2016)
Beluch, W.H., Genewein, T., Nürnberger, A., Köhler, J.M.: The power of ensembles for active learning in image classification. In: CVPR, pp. 9368–9377. IEEE Computer Society (2018)
Berrendorf, M., Faerman, E., Melnychuk, V., Tresp, V., Seidl, T.: Knowledge graph entity alignment with graph convolutional networks: lessons learned. arXiv preprint arXiv:1911.08342 (2019)
Berrendorf, M., Faerman, E., Vermue, L., Tresp, V.: Interpretable and fair comparison of link prediction or entity alignment methods with adjusted mean rank. arXiv preprint arXiv:2002.06914 (2020)
Cai, H., Zheng, V.W., Chang, K.C.C.: Active learning for graph embedding. arXiv preprint arXiv:1705.05085 (2017)
Cao, Y., Liu, Z., Li, C., Liu, Z., Li, J., Chua, T.: Multi-channel graph neural network for entity alignment. In: ACL, vol. 1, pp. 1452–1461. ACL (2019)
Chen, M., Tian, Y., Yang, M., Zaniolo, C.: Multilingual knowledge graph embeddings for cross-lingual knowledge alignment. In: IJCAI, pp. 1511–1517. ijcai.org (2017)
Cortés, X., Serratosa, F.: Active-learning query strategies applied to select a graph node given a graph labelling. In: Kropatsch, W.G., Artner, N.M., Haxhimusa, Y., Jiang, X. (eds.) GbRPR 2013. LNCS, vol. 7877, pp. 61–70. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38221-5_7
Cortés, X., Serratosa, F., Solé-Ribalta, A.: Active graph matching based on pairwise probabilities between nodes. In: Gimel’farb, G., et al. (eds.) SSPR /SPR 2012. LNCS, vol. 7626, pp. 98–106. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-34166-3_11
Das, K., Samanta, S., Pal, M.: Study on centrality measures in social networks: a survey. Soc. Netw. Anal. Min. 8(1), 1–11 (2018). https://doi.org/10.1007/s13278-018-0493-2
Dietz, L., Kotov, A., Meij, E.: Utilizing knowledge graphs for text-centric information retrieval. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, SIGIR 2018, pp. 1387–1390. Association for Computing Machinery, New York (2018). https://doi.org/10.1145/3209978.3210187
Faerman, E., Borutta, F., Fountoulakis, K., Mahoney, M.W.: LASAGNE: locality and structure aware graph node embedding. In: WI, pp. 246–253. IEEE Computer Society (2018)
Faerman, E., Voggenreiter, O., Borutta, F., Emrich, T., Berrendorf, M., Schubert, M.: Graph alignment networks with node matching scores. In: Graph Representation Learning NeurIPS 2019 Workshop (2019)
Gal, Y.: Uncertainty in deep learning. Ph.D. thesis, University of Cambridge (2016)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: ICML JMLR Workshop and Conference Proceedings, vol. 48, pp. 1050–1059. JMLR.org (2016)
Gal, Y., Islam, R., Ghahramani, Z.: Deep Bayesian active learning with image data. In: Proceedings of Machine Learning Research (ICML), vol. 70, pp. 1183–1192. PMLR (2017)
Gao, L., Yang, H., Zhou, C., Wu, J., Pan, S., Hu, Y.: Active discriminative network representation learning. In: IJCAI, pp. 2142–2148. ijcai.org (2018)
Geifman, Y., El-Yaniv, R.: Deep active learning over the long tail. arXiv preprint arXiv:1711.00941 (2017)
Guo, L., Sun, Z., Hu, W.: Learning to exploit long-term relational dependencies in knowledge graphs. In: Proceedings of Machine Learning Research (ICML), vol. 97, pp. 2505–2514. PMLR (2019)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Houlsby, N., Huszár, F., Ghahramani, Z., Lengyel, M.: Bayesian active learning for classification and preference learning. arXiv preprint arXiv:1112.5745 (2011)
Lewis, D.D., Catlett, J.: Heterogeneous uncertainty sampling for supervised learning. In: ICML, pp. 148–156. Morgan Kaufmann (1994)
Li, C., Cao, Y., Hou, L., Shi, J., Li, J., Chua, T.: Semi-supervised entity alignment via joint knowledge embedding model and cross-graph model. In: EMNLP/IJCNLP, vol. 1, pp. 2723–2732. ACL (2019)
Li, Y., Gu, C., Dullien, T., Vinyals, O., Kohli, P.: Graph matching networks for learning the similarity of graph structured objects. In: Proceedings of Machine Learning Research (ICML), vol. 97, pp. 3835–3845. PMLR (2019)
Mahdisoltani, F., Biega, J., Suchanek, F.M.: YAGO3: a knowledge base from multilingual wikipedias. In: CIDR (2015). www.cidrdb.org
Malmi, E., Gionis, A., Terzi, E.: Active network alignment: a matching-based approach. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp. 1687–1696 (2017)
Ostapuk, N., Yang, J., Cudré-Mauroux, P.: ActiveLink: deep active learning for link prediction in knowledge graphs. In: WWW, pp. 1398–1408. ACM (2019)
Pei, S., Yu, L., Hoehndorf, R., Zhang, X.: Semi-supervised entity alignment via knowledge graph embedding with awareness of degree difference. In: WWW, pp. 3130–3136. ACM (2019)
Puthal, D., Nepal, S., Paris, C., Ranjan, R., Chen, J.: Efficient algorithms for social network coverage and reach. In: BigData Congress, pp. 467–474. IEEE Computer Society (2015)
Sener, O., Savarese, S.: Active learning for convolutional neural networks: a core-set approach. In: ICLR (Poster). OpenReview.net (2018)
Settles, B.: Active learning literature survey. University of Wisconsin-Madison Department of Computer Sciences, Technical report (2009)
Shen, Y., Yun, H., Lipton, Z.C., Kronrod, Y., Anandkumar, A.: Deep active learning for named entity recognition. In: ICLR (Poster). OpenReview.net (2018)
Speer, R., Chin, J., Havasi, C.: Conceptnet 5.5: an open multilingual graph of general knowledge. In: AAAI, pp. 4444–4451. AAAI Press (2017)
Sun, Z., Hu, W., Li, C.: Cross-lingual entity alignment via joint attribute-preserving embedding. In: d’Amato, C., et al. (eds.) ISWC 2017. LNCS, vol. 10587, pp. 628–644. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68288-4_37
Sun, Z., Hu, W., Zhang, Q., Qu, Y.: Bootstrapping entity alignment with knowledge graph embedding. In: IJCAI, pp. 4396–4402 (2018)
Sun, Z., et al.: Knowledge graph alignment network with gated multi-hop neighborhood aggregation. arXiv preprint arXiv:1911.08936 (2019)
Trisedya, B.D., Qi, J., Zhang, R.: Entity alignment between knowledge graphs using attribute embeddings. In: AAAI, pp. 297–304. AAAI Press (2019)
Vrandečić, D., Krötzsch, M.: Wikidata: a free collaborative knowledgebase. Commun. ACM 57(10), 78–85 (2014)
Wang, K., Zhang, D., Li, Y., Zhang, R., Lin, L.: Cost-effective active learning for deep image classification. IEEE Trans. Circ. Syst. Video Techn. 27(12), 2591–2600 (2017)
Wang, Z., Lv, Q., Lan, X., Zhang, Y.: Cross-lingual knowledge graph alignment via graph convolutional networks. In: EMNLP, pp. 349–357. ACL (2018)
Wu, Y., Xu, Y., Singh, A., Yang, Y., Dubrawski, A.: Active learning for graph neural networks via node feature propagation. arXiv preprint arXiv:1910.07567 (2019)
Xu, K., et al.: Cross-lingual knowledge graph alignment via graph matching neural network. In: ACL, vol. 1, pp. 3156–3161. ACL (2019)
Yang, L., Zhang, Y., Chen, J., Zhang, S., Chen, D.Z.: Suggestive annotation: a deep active learning framework for biomedical image segmentation. In: Descoteaux, M., et al. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 399–407. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66179-7_46
Zhang, Q., Sun, Z., Hu, W., Chen, M., Guo, L., Qu, Y.: Multi-view knowledge graph embedding for entity alignment. In: IJCAI, pp. 5429–5435. ijcai.org (2019)
Zhang, Y., Lease, M., Wallace, B.C.: Active discriminative text representation learning. In: AAAI, pp. 3386–3392. AAAI Press (2017)
Zhu, Q., Zhou, X., Wu, J., Tan, J., Guo, L.: Neighborhood-aware attentional representation for multilingual knowledge graphs. In: IJCAI, pp. 1943–1949. ijcai.org (2019)
Acknowledgement
This work has been funded by the German Federal Ministry of Education and Research (BMBF) under Grant No. 01IS18036A. The authors of this work take full responsibilities for its content.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Berrendorf, M., Faerman, E., Tresp, V. (2021). Active Learning for Entity Alignment. In: Hiemstra, D., Moens, MF., Mothe, J., Perego, R., Potthast, M., Sebastiani, F. (eds) Advances in Information Retrieval. ECIR 2021. Lecture Notes in Computer Science(), vol 12656. Springer, Cham. https://doi.org/10.1007/978-3-030-72113-8_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-72113-8_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-72112-1
Online ISBN: 978-3-030-72113-8
eBook Packages: Computer ScienceComputer Science (R0)