Zero-Shot Learning with Common Sense Knowledge Graphs
This addresses the problem of predicting unseen classes without labeled examples for researchers in AI, offering a novel approach but with incremental gains in specific benchmarks.
The paper tackles zero-shot learning by using common sense knowledge graphs to generate class representations, achieving improvements over WordNet-based methods on five out of six benchmark datasets in language and vision.
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.