Improving Zero Shot Learning Baselines with Commonsense Knowledge

by   Abhinaba Roy, et al.
University of Michigan
Nanyang Technological University

Zero shot learning – the problem of training and testing on a completely disjoint set of classes – relies greatly on its ability to transfer knowledge from train classes to test classes. Traditionally semantic embeddings consisting of human defined attributes (HA) or distributed word embeddings (DWE) are used to facilitate this transfer by improving the association between visual and semantic embeddings. In this paper, we take advantage of explicit relations between nodes defined in ConceptNet, a commonsense knowledge graph, to generate commonsense embeddings of the class labels by using a graph convolution network-based autoencoder. Our experiments performed on three standard benchmark datasets surpass the strong baselines when we fuse our commonsense embeddings with existing semantic embeddings i.e. HA and DWE.


VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning

Human-annotated attributes serve as powerful semantic embeddings in zero...

Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense Reasoning

Commonsense reasoning systems should be able to generalize to diverse re...

Visually Aligned Word Embeddings for Improving Zero-shot Learning

Zero-shot learning (ZSL) highly depends on a good semantic embedding to ...

Learning Graph-Based Priors for Generalized Zero-Shot Learning

The task of zero-shot learning (ZSL) requires correctly predicting the l...

OntoZSL: Ontology-enhanced Zero-shot Learning

Zero-shot Learning (ZSL), which aims to predict for those classes that h...

Exploiting Sentiment and Common Sense for Zero-shot Stance Detection

The stance detection task aims to classify the stance toward given docum...

Zero-Shot Learning with Common Sense Knowledge Graphs

Zero-shot learning relies on semantic class representations such as attr...

Please sign up or login with your details

Forgot password? Click here to reset