One-Shot Relational Learning for Knowledge Graphs
Preprint
Abstract
Knowledge graphs (KGs) are the key components of various natural language processing applications. To further expand KGs' coverage, previous studies on knowledge graph completion usually require a large number of training instances for each relation. However, we observe that long-tail relations are actually more common in KGs and those newly added relations often do not have many known triples for training. In this work, we aim at predicting new facts under a challenging setting where only one training instance is available. We propose a one-shot relational learning framework, which utilizes the knowledge extracted by embedding models and learns a matching metric by considering both the learned embeddings and one-hop graph structures. Empirically, our model yields considerable performance improvements over existing embedding models, and also eliminates the need of re-training the embedding models when dealing with newly added relations.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Never-ending learningCommunications of the ACM, 2018
- Convolutional 2D Knowledge Graph EmbeddingsProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Open-World Knowledge Graph CompletionProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Diverse Few-Shot Text Classification with Multiple Metrics2018
- DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning2017
- Representation Learning of Knowledge Graphs with Entity DescriptionsProceedings of the AAAI Conference on Artificial Intelligence, 2016
- Learning Entity and Relation Embeddings for Knowledge Graph CompletionProceedings of the AAAI Conference on Artificial Intelligence, 2015
- Modeling Relation Paths for Representation Learning of Knowledge Bases2015
- Relational retrieval using a combination of path-constrained random walksMachine Learning, 2010
- Toward an Architecture for Never-Ending Language LearningProceedings of the AAAI Conference on Artificial Intelligence, 2010