{"type":"ScholarlyArticle","title":"Neighborhood-Aware Attentional Representation for Multilingual Knowledge Graphs","authors":[{"name":"Qiannan Zhu","slug":"qiannan-zhu","given":"Qiannan","family":"Zhu","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China; School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China"},{"name":"Xiaofei Zhou","slug":"xiaofei-zhou","given":"Xiaofei","family":"Zhou","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China; School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China"},{"name":"Jia Wu","slug":"jia-wu","given":"Jia","family":"Wu","affiliation":"Department of Computing , Macquarie University , Sydney , Australia"},{"name":"Jianlong Tan","slug":"jianlong-tan","given":"Jianlong","family":"Tan","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China; School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China"},{"name":"Li Guo","slug":"li-guo","given":"Li","family":"Guo","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China; School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China"}],"abstract":"Multilingual knowledge graphs constructed by entity alignment are the indispensable resources for numerous AI-related applications. Most existing entity alignment methods only use the triplet-based knowledge to find the aligned entities across multilingual knowledge graphs, they usually ignore the neighborhood subgraph knowledge of entities that implies more richer alignment information for aligning entities. In this paper, we incorporate neighborhood subgraph-level information of entities, and propose a neighborhood-aware attentional representation method NAEA for multilingual knowledge graphs. NAEA devises an attention mechanism to learn neighbor-level representation by aggregating neighbors' representations with a weighted combination. The attention mechanism enables entities not only capture different impacts of their neighbors on themselves, but also attend over their neighbors' feature representations with different importance. We evaluate our model on two real-world datasets DBP15K and DWY100K, and the experimental results show that the proposed model NAEA significantly and consistently outperforms state-of-the-art entity alignment models.","doi":"10.24963/ijcai.2019/269","url":"https://ijcai.org/proceedings/2019/269","pdf":"https://ijcai.org/proceedings/2019/0269.pdf","markdown":"https://ijcai.org/proceedings/2019/269.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/269","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Knowledge Representation and Reasoning","track":"Main track","number":269,"pages":{"first":1943,"last":1949},"keywords":["Knowledge Representation and Reasoning: Knowledge Representation and Decision ; Utility Theory","Machine Learning: Knowledge-based Learning"],"videos":[],"references":[{"position":1,"raw":"[Abney, 2004] Steven P. Abney. Understanding the yarowsky algorithm. Computational Linguistics, 30(3):365-395, 2004.","title":"Understanding the yarowsky algorithm","authors":"P Steven, Abney","year":"2004","venue":"Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bizer et al., 2009] Christian Bizer, Jens Lehmann, Georgi Kobilarov, Sören Auer, Christian Becker, Richard Cyga- niak, and Sebastian Hellmann. Dbpedia A crystalliza- tion point for the web of data. J. Web Sem., 7(3):154-165, 2009.","title":"Dbpedia A crystallization point for the web of data","authors":"Bizer","year":"2009","venue":"J. Web Sem","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bordes et al., 2013] A. Bordes, N. Usunier, and A. Garcia- Duran. Translating embeddings for modeling multi- relational data. In Proceedinds of NIPS, pages 2787-2795, 2013.","title":"Translating embeddings for modeling multirelational data","authors":"A Bordes, N Usunier, A Garcia-Duran","year":"2013","venue":"Proceedinds of NIPS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2017] Muhao Chen, Yingtao Tian, Mohan Yang, and Carlo Zaniolo. Multilingual knowledge graph embeddings for cross-lingual knowledge alignment. In Proceedinds of IJCAI, pages 1511-1517, 2017.","title":"Multilingual knowledge graph embeddings for cross-lingual knowledge alignment","authors":"Chen","year":"2017","venue":"Proceedinds of IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/209"},{"position":5,"raw":"[Dettmers et al., 2018] Tim Dettmers, Pasquale Minervini, Pontus Stenetorp, and Sebastian Riedel. Convolutional 2d knowledge graph embeddings. In AAAI, pages 1811-1818, 2018.","title":"Convolutional 2d knowledge graph embeddings","authors":"Tim Dettmers, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[García-Durán et al., 2015] Alberto García-Durán, Antoine Bordes, and Nicolas Usunier. Composing relationships with translations. In EMNLP, pages 286-290, 2015.","title":"Composing relationships with translations","authors":"Alberto García-Durán, Antoine Bordes, Nicolas Usunier","year":"2015","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ji et al., 2015] G. Ji, S. He, L. Xu, K. Liu, and J. Zhao. Knowledge graph embedding via dynamic mapping ma- trix. In Proceedinds of ACL, pages 687-696, 2015.","title":"Knowledge graph embedding via dynamic mapping matrix","authors":"G Ji, S He, L Xu, K Liu, J Zhao","year":"2015","venue":"Proceedinds of ACL","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Lacoste-Julien et al., 2013] Simon Lacoste-Julien, Kon- stantina Palla, Alex Davies, Gjergji Kasneci, Thore Grae- pel, and Zoubin Ghahramani. Sigma: simple greedy matching for aligning large knowledge bases. In KDD, pages 572-580, 2013.","title":"Sigma: simple greedy matching for aligning large knowledge bases","authors":"Simon Lacoste-Julien, Konstantina Palla, Alex Davies, Gjergji Kasneci, Thore Graepel, Zoubin Ghahramani","year":"2013","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lin et al., 2015a] Y. Lin, Z. Liu, M. Sun, Y. Liu, and X. Zhu. Learning entity and relation embeddings for knowledge graph completion. In Proceedinds of AAAI, pages 2181- 2187, 2015.","title":"Learning entity and relation embeddings for knowledge graph completion","authors":"Lin","year":"2015","venue":"Proceedinds of AAAI","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lin et al., 2015b] Yankai Lin, Zhiyuan Liu, Huan-Bo Luan, Maosong Sun, Siwei Rao, and Song Liu. Modeling rela- tion paths for representation learning of knowledge bases. In EMNLP, pages 705-714, 2015.","title":"Modeling relation paths for representation learning of knowledge bases","authors":"Lin","year":"2015","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu et al., 2017] Weiwei Liu, Ivor W. Tsang, and Klaus- Robert Müller. An easy-to-hard learning paradigm for multiple classes and multiple labels. Journal of Machine Learning Research, 18:94:1-94:38, 2017.","title":"An easy-to-hard learning paradigm for multiple classes and multiple labels","authors":"Weiwei Liu, Ivor W Tsang, Klaus-Robert Müller","year":"2017","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu et al., 2019] Weiwei Liu, Donna Xu, Ivor W. Tsang, and Wenjie Zhang. Metric learning for multi-output tasks. IEEE TPAMI, 41(2):408-422, 2019.","title":"Metric learning for multi-output tasks","authors":"Weiwei Liu, Donna Xu, Ivor W Tsang, Wenjie Zhang","year":"2019","venue":"IEEE TPAMI","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Mahdisoltani et al., 2015] Farzaneh Mahdisoltani, Joanna Biega, and Fabian Suchanek. Yago3: A knowledge base from multilingual wikipedias. In CIDR, 2015.","title":"Yago3: A knowledge base from multilingual wikipedias","authors":"Farzaneh Mahdisoltani, Joanna Biega, Fabian Suchanek","year":"2015","venue":"CIDR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Nickel et al., 2016] Maximilian Nickel, Lorenzo Rosasco, and Tomaso Poggio. Holographic embeddings of knowl- edge graphs. Computer Science, 2016.","title":"Holographic embeddings of knowledge graphs","authors":"Maximilian Nickel, Lorenzo Rosasco, Tomaso Poggio","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Shi and Weninger, 2017] B. Shi and T. Weninger. Proje: Embedding projection for knowledge graph completion. In AAAI, pages 1236-1242, 2017.","title":"Proje: Embedding projection for knowledge graph completion","authors":"Weninger Shi, ] B Shi, T Weninger","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Socher et al., 2013] Richard Socher, Danqi Chen, Christo- pher D. Manning, and Andrew Y. Ng. Reasoning with neural tensor networks for knowledge base completion. In NIPS, pages 926-934, 2013.","title":"Reasoning with neural tensor networks for knowledge base completion","authors":"Richard Socher, Danqi Chen, Christopher D Manning, Andrew Y Ng","year":"2013","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Suchanek et al., 2008] Fabian M. Suchanek, Gjergji Kas- neci, and Gerhard Weikum. YAGO: A large ontology from wikipedia and wordnet. J. Web Sem., 6(3):203-217, 2008.","title":"YAGO: A large ontology from wikipedia and wordnet","authors":"Fabian M Suchanek, Gjergji Kasneci, Gerhard Weikum","year":"2008","venue":"J. Web Sem","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Suchanek et al., 2011] Fabian M. Suchanek, Serge Abite- boul, and Pierre Senellart. PARIS: probabilistic alignment of relations, instances, and schema. CoRR, abs/1111.7164, 2011.","title":"PARIS: probabilistic alignment of relations, instances, and schema","authors":"Fabian M Suchanek, Serge Abiteboul, Pierre Senellart","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Sun et al., 2017] Zequn Sun, Wei Hu, and Chengkai Li. Cross-lingual entity alignment via joint attribute- preserving embedding. In Proceedinds of ISWC, pages 628-644, 2017.","title":"Cross-lingual entity alignment via joint attributepreserving embedding","authors":"Sun","year":"2017","venue":"Proceedinds of ISWC","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Sun et al., 2018] Zequn Sun, Wei Hu, Qingheng Zhang, and Yuzhong Qu. Bootstrapping entity alignment with knowl- edge graph embedding. In IJCAI, pages 4396-4402, 2018.","title":"Bootstrapping entity alignment with knowledge graph embedding","authors":"Zequn Sun, Wei Hu, Qingheng Zhang, Yuzhong Qu","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/611"},{"position":21,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NIPS, pages 6000-6010, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Vrandecic, 2012] Denny Vrandecic. Wikidata: A new plat- form for collaborative data collection. In WWW, 2012.","title":"Wikidata: A new platform for collaborative data collection","authors":"Denny Vrandecic","year":"2012","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2013] Zhichun Wang, Juanzi Li, and Jie Tang. Boosting cross-lingual knowledge linking via concept an- notation. In IJCAI, pages 2733-2739, 2013.","title":"Boosting cross-lingual knowledge linking via concept annotation","authors":"Zhichun Wang, Juanzi Li, Jie Tang","year":"2013","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2013/402"},{"position":24,"raw":"[Wang et al., 2014] Z. Wang, J. Zhang, J. Feng, and Z. Chen. Knowledge graph embedding by translating on hyper- planes. In Proceedinds of AAAI, pages 1112-1119, 2014.","title":"Knowledge graph embedding by translating on hyperplanes","authors":"Z Wang, J Zhang, J Feng, Z Chen","year":"2014","venue":"Proceedinds of AAAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yang et al., 2015] B. Yang, W. t. Yih, X. He, J. Gao, and L. Deng. Learning multi-relational semantics using neural-embedding models. In ICLR, 2015.","title":"Learning multi-relational semantics using neural-embedding models","authors":"B Yang, W T Yih, X He, J Gao, L Deng","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yarowsky, 1995] David Yarowsky. Unsupervised word sense disambiguation rivaling supervised methods. In A- CL, pages 189-196, 1995.","title":"Unsupervised word sense disambiguation rivaling supervised methods","authors":"David Yarowsky","year":"1995","venue":"A-CL","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhang et al., 2015] Duo Zhang, Benjamin I. P. Rubinstein, and Jim Gemmell. Principled graph matching algorithm- s for integrating multiple data sources. IEEE TKDE., 27(10):2784-2796, 2015.","title":"Principled graph matching algorithms for integrating multiple data sources","authors":"Duo Zhang, I P Benjamin, Jim Rubinstein, Gemmell","year":"2015","venue":"IEEE TKDE","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhou et al., 2017] Xiaofei Zhou, Qiannan Zhu, Ping Liu, and Li Guo. Learning knowledge embeddings by combin- ing limit-based scoring loss. In CIKM, pages 1009-1018, 2017.","title":"Learning knowledge embeddings by combining limit-based scoring loss","authors":"Xiaofei Zhou, Qiannan Zhu, Ping Liu, Li Guo","year":"2017","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhu et al., 2017] Hao Zhu, Ruobing Xie, Zhiyuan Liu, and Maosong Sun. Iterative entity alignment via joint knowl- edge embeddings. In IJCAI, pages 4258-4264, 2017.","title":"Iterative entity alignment via joint knowledge embeddings","authors":"Ruobing Hao Zhu, Zhiyuan Xie, Maosong Liu, Sun","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/595"},{"position":30,"raw":"[Zhu et al., 2019] Qiannan Zhu, Xiaofei Zhou, Peng Zhang, and Yong Shi. A neural translating general hyperplane for knowledge graph embedding. J. Comput. Science, 30:108- 117, 2019.","title":"A neural translating general hyperplane for knowledge graph embedding","authors":"Qiannan Zhu, Xiaofei Zhou, Peng Zhang, Yong Shi","year":"2019","venue":"J. Comput. Science","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}