CLAug 27, 2018

One-Shot Relational Learning for Knowledge Graphs

arXiv:1808.09040v11160 citations
AI Analysis

This addresses the challenge of long-tail and newly added relations in knowledge graphs, which are common but lack sufficient training data.

The paper tackles the problem of predicting new facts in knowledge graphs when only one training instance is available for a relation, achieving considerable performance improvements over existing embedding models.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes