TY - GEN
T1 - Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion
AU - Tang, Zhenwei
AU - Pei, Shichao
AU - Zhang, Zhao
AU - Zhu, Yongchun
AU - Zhuang, Fuzhen
AU - Hoehndorf, Robert
AU - Zhang, Xiangliang
N1 - Publisher Copyright:
© 2022 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85137932267&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85137932267
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 2248
EP - 2254
BT - Proceedings of the 31st International Joint Conference on Artificial Intelligence, IJCAI 2022
A2 - De Raedt, Luc
A2 - De Raedt, Luc
PB - International Joint Conferences on Artificial Intelligence Organization
T2 - 31st International Joint Conference on Artificial Intelligence, IJCAI 2022
Y2 - 23 July 2022 through 29 July 2022
ER -