{"type":"ScholarlyArticle","title":"Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion","authors":[{"name":"Zhenwei Tang","slug":"zhenwei-tang","given":"Zhenwei","family":"Tang","affiliation":"King Abdullah University of Science and Technology"},{"name":"Shichao Pei","slug":"shichao-pei","given":"Shichao","family":"Pei","affiliation":"King Abdullah University of Science and Technology"},{"name":"Zhao Zhang","slug":"zhao-zhang","given":"Zhao","family":"Zhang","affiliation":"Institute of Computing Technology , Chinese Academy of Sciences"},{"name":"Yongchun Zhu","slug":"yongchun-zhu","given":"Yongchun","family":"Zhu","affiliation":"Institute of Computing Technology , Chinese Academy of Sciences"},{"name":"Fuzhen Zhuang","slug":"fuzhen-zhuang","given":"Fuzhen","family":"Zhuang","affiliation":"Institute of Artificial Intelligence , Beihang University; SKLSDE , School of Computer Science , Beihang University"},{"name":"Robert Hoehndorf","slug":"robert-hoehndorf","given":"Robert","family":"Hoehndorf","affiliation":"King Abdullah University of Science and Technology"},{"name":"Xiangliang Zhang","slug":"xiangliang-zhang","given":"Xiangliang","family":"Zhang","affiliation":"University of Notre Dame; King Abdullah University of Science and Technology"}],"abstract":"Most real-world knowledge graphs (KG) are far from complete and comprehensive. This problem has motivated efforts in predicting the most plausible missing facts to complete a given KG, i.e., knowledge graph completion (KGC). However, existing KGC methods suffer from two main issues, 1) the false negative issue, i.e., the sampled negative training instances may include potential true facts; and 2) the data sparsity issue, i.e., true facts account for only a tiny part of all possible facts. To this end, we propose positive-unlabeled learning with adversarial data augmentation (PUDA) for KGC. In particular, PUDA tailors positive-unlabeled risk estimator for the KGC task to deal with the false negative issue. Furthermore, to address the data sparsity issue, PUDA achieves a data augmentation strategy by unifying adversarial training and positive-unlabeled learning under the positive-unlabeled minimax game. Extensive experimental results on real-world benchmark datasets demonstrate the effectiveness and compatibility of our proposed method.","doi":"10.24963/ijcai.2022/312","url":"https://ijcai.org/proceedings/2022/312","pdf":"https://ijcai.org/proceedings/2022/0312.pdf","markdown":"https://ijcai.org/proceedings/2022/312.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/312","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Data Mining","track":"Main Track","number":312,"pages":{"first":2248,"last":2254},"keywords":["Data Mining: Knowledge Graphs and Knowledge Base Completion","Machine Learning: Representation learning"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986505","length_sec":87,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984648","length_sec":304,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Ahrabian et al., 2020] K. Ahrabian, A. Feizi, Y. Salehi, W. Hamil- ton, and Avishek J. Bose. Structure aware negative sampling in knowledge graphs. In EMNLP, pages 6093-6101, 2020.","title":"Structure aware negative sampling in knowledge graphs","authors":"K Ahrabian, A Feizi, Y Salehi, W Hamilton, Avishek J Bose","year":"2020","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Akujuobi et al., 2020] U. Akujuobi, J. Chen, M. Elhoseiny, M. Spranger, and X. Zhang. Temporal positive-unlabeled learn- ing for biomedical hypothesis generation via risk estimation. NeurIPS, 33:4597-4609, 2020.","title":"Temporal positive-unlabeled learning for biomedical hypothesis generation via risk estimation","authors":"U Akujuobi, J Chen, M Elhoseiny, M Spranger, X Zhang","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bekker and Davis, 2020] J. Bekker and J. Davis. Learning from positive and unlabeled data: A survey. Machine Learning, 109(4):719-760, 2020.","title":"Learning from positive and unlabeled data: A survey","authors":"J Bekker, J Davis","year":"2020","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bordes et al., 2013] A. Bordes, N. Usunier, A. Garcia-Duran, J. Weston, and O. Yakhnenko. Translating embeddings for mod- eling multi-relational data. NeurIPS, 26, 2013.","title":"Translating embeddings for modeling multi-relational data","authors":"A Bordes, N Usunier, A Garcia-Duran, J Weston, O Yakhnenko","year":"2013","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Breit et al., 2020] A. Breit, S. Ott, A. Agibetov, and M. Samwald. Openbiolink: a benchmarking framework for large-scale biomed- ical link prediction. Bioinformatics, 36(13):4097-4098, 2020.","title":"Openbiolink: a benchmarking framework for large-scale biomedical link prediction","authors":"A Breit, S Ott, A Agibetov, M Samwald","year":"2020","venue":"Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cai and Wang, 2018] L. Cai and William Y. Wang. Kbgan: Ad- versarial learning for knowledge graph embeddings. In NAACL, pages 1470-1480, 2018.","title":"Kbgan: Adversarial learning for knowledge graph embeddings","authors":"L Cai, William Y Wang","year":"2018","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Christoffel et al., 2016] M. Christoffel, G. Niu, and M. Sugiyama. Class-prior estimation for learning from positive and unlabeled data. In ACML, pages 221-236. PMLR, 2016.","title":"Class-prior estimation for learning from positive and unlabeled data","authors":"M Christoffel, G Niu, M Sugiyama","year":"2016","venue":"ACML","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dettmers et al., 2018] T. Dettmers, P. Minervini, P. Stenetorp, and S. Riedel. Convolutional 2d knowledge graph embeddings. In AAAI, 2018.","title":"Convolutional 2d knowledge graph embeddings","authors":"T Dettmers, P Minervini, P Stenetorp, S Riedel","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Du Plessis et al., 2014] M. Du Plessis, G. Niu, and M. Sugiyama. Analysis of learning from positive and unlabeled data. NeurIPS, 27:703-711, 2014.","title":"Analysis of learning from positive and unlabeled data","authors":"M Du Plessis, G Niu, M Sugiyama","year":"2014","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Du Plessis et al., 2015] M. Du Plessis, G. Niu, and M. Sugiyama. Convex formulation for learning from positive and unlabeled data. In ICML, pages 1386-1394. PMLR, 2015.","title":"Convex formulation for learning from positive and unlabeled data","authors":"M Du Plessis, G Niu, M Sugiyama","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Goodfellow et al., 2014] I.","title":null,"authors":"Goodfellow","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. NeurIPS, 27, 2014.","title":"Generative adversarial nets","authors":"J Goodfellow, M Pouget-Abadie, B Mirza, D Xu, S Warde-Farley, A Ozair, Y Courville, Bengio","year":"2014","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Guo et al., 2020] J. Guo, Y. Fan, L. Pang, L. Yang, Q. Ai, H. Za- mani, C. Wu, W. Croft, and X. Cheng. A deep look into neural ranking models for information retrieval. Information Processing & Management, 57(6):102067, 2020.","title":"A deep look into neural ranking models for information retrieval","authors":"J Guo, Y Fan, L Pang, L Yang, Q Ai, H Zamani, C Wu, W Croft, X Cheng","year":"2020","venue":"Information Processing & Management","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[He et al., 2018] F. He, T. Liu, G. Webb, and D. Tao. Instance- dependent pu learning by bayesian optimal relabeling. arXiv preprint arXiv:1808.02180, 2018.","title":"Instancedependent pu learning by bayesian optimal relabeling","authors":"F He, T Liu, G Webb, D Tao","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kazemi and Poole, 2018] S. Kazemi and D. Poole. Simple embed- ding for link prediction in knowledge graphs. In NeurIPS, pages 4289-4300, 2018.","title":"Simple embedding for link prediction in knowledge graphs","authors":"S Kazemi, D Poole","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kiryo et al., 2017] R. Kiryo, G. Niu, M. du Plessis, and M. Sugiyama. Positive-unlabeled learning with non-negative risk estimator. In NeurIPS, pages 1674-1684, 2017.","title":"Positive-unlabeled learning with non-negative risk estimator","authors":"R Kiryo, G Niu, M Du Plessis, M Sugiyama","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Krompaß et al., 2015] D. Krompaß, S. Baier, and V. Tresp. Type- constrained representation learning in knowledge graphs. In ISWC, pages 640-655, 2015.","title":"Typeconstrained representation learning in knowledge graphs","authors":"D Krompaß, S Baier, V Tresp","year":"2015","venue":"ISWC","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Li et al., 2021] Z. Li, H. Liu, Z. Zhang, T. Liu, and N. Xiong. Learning knowledge graph embedding with heterogeneous rela- tion attention networks. TNNLS, 2021.","title":"Learning knowledge graph embedding with heterogeneous relation attention networks","authors":"Z Li, H Liu, Z Zhang, T Liu, N Xiong","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Liu et al., 2002] B. Liu, W. Lee, P. Yu, and X. Li. Partially super- vised classification of text documents. In ICML, volume 2, pages 387-394. Sydney, NSW, 2002.","title":"Partially supervised classification of text documents","authors":"B Liu, W Lee, P Yu, X Li","year":"2002","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Mariani et al., 2018] G. Mariani, F. Scheidegger, R. Istrate, C. Bekas, and C. Malossi. Bagan: Data augmentation with bal- ancing gan. arXiv preprint arXiv:1803.09655, 2018.","title":"Bagan: Data augmentation with balancing gan","authors":"G Mariani, F Scheidegger, R Istrate, C Bekas, C Malossi","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Melnikov et al., 2016] V. Melnikov, P. Gupta, B. Frick, D. Kaimann, and E. Hüllermeier. Pairwise versus pointwise ranking: A case study. Schedae Informaticae, 2016.","title":"Pairwise versus pointwise ranking: A case study","authors":"V Melnikov, P Gupta, B Frick, D Kaimann, E Hüllermeier","year":"2016","venue":"Schedae Informaticae","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Nguyen et al., 2018] T. Nguyen, D. Nguyen, D. Phung, et al. A novel embedding model for knowledge base completion based on convolutional neural network. In NAACL, pages 327-333, 2018.","title":"A novel embedding model for knowledge base completion based on convolutional neural network","authors":"T Nguyen, D Nguyen, D Phung","year":"2018","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Pujara et al., 2017] J. Pujara, E. Augustine, and L. Getoor. Spar- sity and noise: Where knowledge graph embeddings fall short. In EMNLP, pages 1751-1756, 2017.","title":"Sparsity and noise: Where knowledge graph embeddings fall short","authors":"J Pujara, E Augustine, L Getoor","year":"2017","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Rendle et al., 2009] S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme. Bpr: Bayesian personalized ranking from implicit feedback. In UAI, pages 452-461, 2009.","title":"Bpr: Bayesian personalized ranking from implicit feedback","authors":"S Rendle, C Freudenthaler, Z Gantner, L Schmidt-Thieme","year":"2009","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Rossi et al., 2021] A. Rossi, D. Barbosa, D. Firmani, A. Matinata, and P. Merialdo. Knowledge graph embedding for link predic- tion: A comparative analysis. TKDD, 15(2):1-49, 2021.","title":"Knowledge graph embedding for link prediction: A comparative analysis","authors":"A Rossi, D Barbosa, D Firmani, A Matinata, P Merialdo","year":"2021","venue":"TKDD","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Shi et al., 2018] H. Shi, S. Pan, J. Yang, and C. Gong. Positive and unlabeled learning via loss decomposition and centroid esti- mation. In IJCAI, pages 2689-2695, 2018.","title":"Positive and unlabeled learning via loss decomposition and centroid estimation","authors":"H Shi, S Pan, J Yang, C Gong","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/373"},{"position":27,"raw":"[Shikhar et al., 2020] V. Shikhar, S. Soumya, N. Vikram, and T. Partha. Composition-based multi-relational graph convolu- tional networks. In ICLR, 2020.","title":"Composition-based multi-relational graph convolutional networks","authors":"V Shikhar, S Soumya, N Vikram, T Partha","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Sun et al., 2018] Z. Sun, Z. Deng, J. Nie, and J. Tang. Rotate: Knowledge graph embedding by relational rotation in complex space. In ICLR, 2018.","title":"Rotate: Knowledge graph embedding by relational rotation in complex space","authors":"Z Sun, Z Deng, J Nie, J Tang","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Toutanova et al., 2015] K. Toutanova, D. Chen, P. Pantel, H. Poon, P. Choudhury, and M. Gamon. Representing text for joint embed- ding of text and knowledge bases. In EMNLP, pages 1499-1509, 2015.","title":"Representing text for joint embedding of text and knowledge bases","authors":"K Toutanova, D Chen, P Pantel, H Poon, P Choudhury, M Gamon","year":"2015","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Trouillon et al., 2017] T. Trouillon, C. Dance, É. Gaussier, J. Welbl, S. Riedel, and G. Bouchard. Knowledge graph com- pletion via complex tensor factorization. JMLR, 18:1-38, 2017.","title":"Knowledge graph completion via complex tensor factorization","authors":"T Trouillon, C Dance, É Gaussier, J Welbl, S Riedel, G Bouchard","year":"2017","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wang et al., 2017] J. Wang, L. Yu, W. Zhang, Y. Gong, Y. Xu, B. Wang, P. Zhang, and D. Zhang. Irgan: A minimax game for unifying generative and discriminative information retrieval models. In SIGIR, pages 515-524, 2017.","title":"Irgan: A minimax game for unifying generative and discriminative information retrieval models","authors":"J Wang, L Yu, W Zhang, Y Gong, Y Xu, B Wang, P Zhang, D Zhang","year":"2017","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Wang et al., 2018] P. Wang, S. Li, and R. Pan. Incorporating gan for negative sampling in knowledge representation learning. In AAAI, volume 32, 2018.","title":"Incorporating gan for negative sampling in knowledge representation learning","authors":"P Wang, S Li, R Pan","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Xu and Denil, 2019] D. Xu and M. Denil. Positive-unlabeled re- ward learning. arXiv preprint arXiv:1911.00459, 2019.","title":"Positive-unlabeled reward learning","authors":"D Xu, M Denil","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Yang et al., 2014] B. Yang, W. Yih, X. He, J. Gao, and L. Deng. Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint arXiv:1412.6575, 2014.","title":"Embedding entities and relations for learning and inference in knowledge bases","authors":"B Yang, W Yih, X He, J Gao, L Deng","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Zhang et al., 2019a] W. Zhang, B. Paudel, W. Zhang, A. Bernstein, and H. Chen. Interaction embeddings for prediction and expla- nation in knowledge graphs. In WSDM, pages 96-104, 2019.","title":"Interaction embeddings for prediction and explanation in knowledge graphs","authors":"Zhang","year":"2019","venue":"WSDM","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zhang et al., 2019b] Y. Zhang, Q. Yao, Y. Shao, and L. Chen. Nscaching: simple and efficient negative sampling for knowledge graph embedding. In ICDE, pages 614-625. IEEE, 2019.","title":"Nscaching: simple and efficient negative sampling for knowledge graph embedding","authors":"Zhang","year":"2019","venue":"ICDE","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Zhang et al., 2020] Z. Zhang, F. Zhuang, H. Zhu, Z. Shi, H. Xiong, and Q. He. Relational graph neural network with hierarchical attention for knowledge graph completion. In AAAI, volume 34, pages 9612-9619, 2020.","title":"Relational graph neural network with hierarchical attention for knowledge graph completion","authors":"Z Zhang, F Zhuang, H Zhu, Z Shi, H Xiong, Q He","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}