About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Nihal V. Nayak
- sl:arxiv_num : 2006.10713
- sl:arxiv_published : 2020-06-18T17:46:17Z
- sl:arxiv_summary : 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.@en
- sl:arxiv_title : Zero-Shot Learning with Common Sense Knowledge Graphs@en
- sl:arxiv_updated : 2022-08-25T19:27:00Z
- sl:bookmarkOf : https://arxiv.org/abs/2006.10713
- sl:creationDate : 2022-08-29
- sl:creationTime : 2022-08-29T15:42:01Z
Documents with similar tags (experimental)