Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning
Uncertain knowledge graphs (UKGs) associate each triple with a confidence score to provide more precise knowledge representations. Recently, since real-world UKGs suffer from the incompleteness, uncertain knowledge graph (UKG) completion attracts more attention, aiming to complete missing triples and confidences. Current studies attempt to learn UKG embeddings to solve this problem, but they neglect the extremely imbalanced distributions of triple confidences. This causes that the learnt embeddings are insufficient to high-quality UKG completion. Thus, in this paper, to address the above issue, we propose a new semi-supervised Confidence Distribution Learning (ssCDL) method for UKG completion, where each triple confidence is transformed into a confidence distribution to introduce more supervision information of different confidences to reinforce the embedding learning process. ssCDL iteratively learns UKG embedding by relational learning on labeled data (i.e., existing triples with confidences) and unlabeled data with pseudo labels (i.e., unseen triples with the generated confidences), which are predicted by meta-learning to augment the training data and rebalance the distribution of triple confidences. Experiments on two UKG datasets demonstrate that ssCDL consistently outperforms state-of-the-art baselines in different evaluation metrics.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge Graph CompletionKnowledge GraphsSimilar Papers 제목 키워드 기반
Trustworthy Knowledge Graph Completion Based on Multi-sourced Noisy Data
Knowledge graphs (KGs) have become a valuable asset for many AI applications. Although some KGs contain plenty of facts, they are widely acknowledged as incomplete. To address this issue, many KG completion methods are p…
Graph Neural NetworkKnowledge Graph CompletionKnowledge GraphsUncertainty-Aware Relational Graph Neural Network for Few-Shot Knowledge Graph Completion
Few-shot knowledge graph completion (FKGC) aims to query the unseen facts of a relation given its few-shot reference entity pairs. The side effect of noises due to the uncertainty of entities and triples may limit the fe…
Few-Shot LearningGraph Neural NetworkKnowledge Graph CompletionAutoencoder-based Graph Construction for Semi-supervised Learning
We consider graph-based semi-supervised learning that leverages a similarity graph across data points to better exploit data structure exposed in unlabeled data. One challenge that arises in this problem context is that …
graph constructionMatrix CompletionOn the Use of Entity Embeddings from Pre-Trained Language Models for Knowledge Graph Completion
Recent work has found that entity representations can be extracted from pre-trained language models to develop knowledge graph completion models that are more robust to the naturally occurring sparsity found in knowledge…
Entity EmbeddingsKnowledge Graph CompletionKnowledge GraphsLanguage Modeling+2Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion
Real-world sensors often produce incomplete, irregular, and noisy point clouds, making point cloud completion increasingly important. However, most existing completion methods rely on large paired datasets for training, …
Point Cloud Completion