A Probabilistic Framework for Knowledge Graph Data Augmentation

Abstract

We present NNMFAug, a probabilistic framework to perform data augmentation for the task of knowledge graph completion to counter the problem of data scarcity, which can enhance the learning process of neural link predictors. Our method can generate potentially diverse triples with the advantage of being efficient and scalable as well as agnostic to the choice of the link prediction model and dataset used. Experiments and analysis done on popular models and benchmarks show that NNMFAug can bring notable improvements over the baselines.

References in corpus (6)

• A Review of Relational Machine Learning for Knowledge Graphs
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Generalizing to Unseen Domains via Adversarial Data Augmentation
• Further advantages of data augmentation on convolutional neural networks
• Open Question Answering with Weakly Supervised Embedding Models
• Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward