.png){kind=icon}
返回
Prototypical Concept Representation
.png){kind=icon}
PRE
AI
DOI：10.1109/TKDE.2022.3180886.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Concepts are building blocks of human thinking. For machines, concept understanding has also been increasingly important, which makes concept representation a fundamental problem in artificial intelligence. While many concepts have their instances, the massive amount of information carried by instances has long been ignored in current concept representation, which limits the usage of these concepts in applications. In this paper, inspired by prototype theory in cognitive science, we propose prototypical concept representation for machines, which represents each concept with a distributed prototype derived from representations of its instances. For prototypical representation learning, we further introduce a novel model named Prototypical Siamese Network (PSN). PSN is trained under the supervision of isA determination, one of the most important concept-related applications. Results of extensive experiments demonstrate that, our method achieves state-of-the-art performance, thus validating the effectiveness of prototypical concept representation.
Keyword:
Concept learning
distributed representations
knowledge graphs
machine learning
期刊
IF:
10.4
论文数:
6.8K
被引数:
3.2W
机构
引用论文
KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation开普勒: 知识嵌入和预训练语言表示的统一模型
OAAI
OAAI分享收藏Impact of Age at Administration, Lysosomal Storage, and Transgene Regulatory Elements on AAV2/8-Mediated Rat Liver Transduction.png)
PLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏Monoclonal Antibodies to Meningococcal Factor H Binding Protein with Overlapping Epitopes and Discordant Functional ActivityPLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏分享收藏Ontogeny of Toll-Like Receptor Mediated Cytokine Responses of South African Infants throughout the First Year of LifePLoS ONEOAAI
PLoS ONEIF0
OAAI分享收藏
查看更多内容