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.
arXiv commentPaper published in TMLR
References in corpus (20)
- Distributed Representations of Words and Phrases and their Compositionality
- Inductive Representation Learning on Large Graphs
- Simplifying Graph Convolutional Networks
- ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
- Snorkel: Rapid Training Data Creation with Weak Supervision
- Graph Transformer Networks
- On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection
- A Generalization of Transformer Networks to Graphs
- Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
- Context-Dependent Fine-Grained Entity Type Tagging
- Leveraging the Invariant Side of Generative Zero-Shot Learning
- Preserving Semantic Relations for Zero-Shot Learning
- Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs
- Learning Dynamic Belief Graphs to Generalize on Text-Based Games
- Neural Module Networks for Reasoning over Text
- Abductive Commonsense Reasoning
- Zero-Shot Learning for Semantic Utterance Classification
- 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