Ridge Regression, Hubness, and Zero-Shot Learning

Abstract

This paper discusses the effect of hubness in zero-shot learning, when ridge regression is used to find a mapping between the example space to the label space. Contrary to the existing approach, which attempts to find a mapping from the example space to the label space, we show that mapping labels into the example space is desirable to suppress the emergence of hubs in the subsequent nearest neighbor search step. Assuming a simple data model, we prove that the proposed approach indeed reduces hubness. This was verified empirically on the tasks of bilingual lexicon extraction and image labeling: hubness was reduced with both of these tasks and the accuracy was improved accordingly.

To be presented at ECML/PKDD 2015

References in corpus (4)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Exploiting Similarities among Languages for Machine Translation
• Zero-Shot Learning by Convex Combination of Semantic Embeddings
• Experiments with Random Projection

Cited by in corpus (14)

• A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings
• Semantic Autoencoder for Zero-Shot Learning
• Preserving Semantic Relations for Zero-Shot Learning
• Transductive Unbiased Embedding for Zero-Shot Learning
• Stacked Semantic-Guided Attention Model for Fine-Grained Zero-Shot Learning
• Learning Unsupervised Word Mapping by Maximizing Mean Discrepancy
• Zero-Shot Visual Recognition via Bidirectional Latent Embedding
• Towards Effective Deep Embedding for Zero-Shot Learning
• Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning
• Generative Dual Adversarial Network for Generalized Zero-shot Learning
• Joint Dictionaries for Zero-Shot Learning
• GTNet: Generative Transfer Network for Zero-Shot Object Detection
• A Biologically Inspired Feature Enhancement Framework for Zero-Shot Learning
• Toward Zero-Shot Unsupervised Image-to-Image Translation