Zero-Shot Learning with Common Sense Knowledge Graphs
arXiv:2006.10713
Abstract
Zero-shot learning relies on semantic class representations such as hand-engineered attributes or learned embeddings to predict classes without any labeled examples. We propose to learn class representations by embedding nodes from common sense knowledge graphs in a vector space. Common sense knowledge graphs are an untapped source of explicit high-level knowledge that requires little human effort to apply to a range of tasks. To capture the knowledge in the graph, we introduce ZSL-KG, a general-purpose framework with a novel transformer graph convolutional network (TrGCN) for generating class representations. Our proposed TrGCN architecture computes non-linear combinations of node neighbourhoods. Our results show that ZSL-KG improves over existing WordNet-based methods on five out of six zero-shot benchmark datasets in language and vision.
Paper published in TMLR
References in corpus (11)
- Simplifying Graph Convolutional Networks
- Snorkel: Rapid Training Data Creation with Weak Supervision
- Graph Transformer Networks
- A Generalization of Transformer Networks to Graphs
- Leveraging the Invariant Side of Generative Zero-Shot Learning
- Learning Dynamic Belief Graphs to Generalize on Text-Based Games
- Neural Module Networks for Reasoning over Text
- Abductive Commonsense Reasoning
- A Meta-Learning Framework for Generalized Zero-Shot Learning
- Isometric Propagation Network for Generalized Zero-shot Learning
- Few-Shot Representation Learning for Out-Of-Vocabulary Words