Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion

About

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.

Zhenwei Tang, Shichao Pei, Zhao Zhang, Yongchun Zhu, Fuzhen Zhuang, Robert Hoehndorf, Xiangliang Zhang• 2022

Related benchmarks

TaskDatasetResultRank
Knowledge Graph ReasoningFB15k-237 (test)
HITS@3 (Avg)0.298
29
Link PredictionTwitter ptb_rate = 0.3 (noisy and incomplete)
MRR1.3
13
Knowledge Graph ReasoningFB15K ptb_rate=0.7 (test)
MRR25.4
12
Knowledge Graph ReasoningFB15K ptb_rate = 0.5 (test)
MRR0.329
12
Knowledge Graph ReasoningFB15K-237 ptb_rate=0.7 (test)
MRR0.165
12
Knowledge Graph ReasoningFB15K-237 ptb_rate = 0.5 (test)
MRR0.202
12
Knowledge Graph ReasoningWN18
MRR0.382
12
Knowledge Graph ReasoningWN18 (test)
MRR0.52
12
Knowledge Graph ReasoningWN18 ptb_rate = 0.5 (test)
MRR0.231
12
Knowledge Graph ReasoningWN18 ptb_rate=0.7 (test)
MRR0.109
12
Showing 10 of 10 rows

Other info

Follow for update