One-Shot Relational Learning for Knowledge Graphs

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.

arXiv commentEMNLP 2018

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Complex Embeddings for Simple Link Prediction
• Matching Networks for One Shot Learning
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
• Order Matters: Sequence to sequence for sets
• Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
• DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
• Modeling Relation Paths for Representation Learning of Knowledge Bases
• Modeling Relational Data with Graph Convolutional Networks
• A Graph-to-Sequence Model for AMR-to-Text Generation
• Diverse Few-Shot Text Classification with Multiple Metrics
• Variational Knowledge Graph Reasoning
• Open-World Knowledge Graph Completion

Cited by in corpus (8)

• Meta-Graph: Few Shot Link Prediction via Meta Learning
• Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embedding
• Building Dynamic Knowledge Graphs from Text-based Games
• Adaptive Attentional Network for Few-Shot Knowledge Graph Completion
• Few-Shot Knowledge Graph Completion
• Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
• A Survey of Embedding Space Alignment Methods for Language and Knowledge Graphs
• Relation Adversarial Network for Low Resource Knowledge Graph Completion