Meta-learning Amidst Heterogeneity and Ambiguity

TL;DR

This paper introduces MAHA, a meta-learning framework designed to effectively handle diverse and ambiguous tasks, improving prediction accuracy and robustness in heterogeneous environments.

Contribution

The paper proposes a novel meta-learning framework that explicitly addresses task heterogeneity and ambiguity, outperforming previous methods in various regression and classification tasks.

Findings

MAHA outperforms existing meta-learning models in prediction accuracy.

The model demonstrates robustness to task heterogeneity.

Experimental results confirm effectiveness in both regression and classification.

Abstract

Meta-learning aims to learn a model that can handle multiple tasks generated from an unknown but shared distribution. However, typical meta-learning algorithms have assumed the tasks to be similar such that a single meta-learner is sufficient to aggregate the variations in all aspects. In addition, there has been less consideration on uncertainty when limited information is given as context. In this paper, we devise a novel meta-learning framework, called Meta-learning Amidst Heterogeneity and Ambiguity (MAHA), that outperforms previous works in terms of prediction based on its ability on task identification. By extensively conducting several experiments in regression and classification, we demonstrate the validity of our model, which turns out to be robust to both task heterogeneity and ambiguity.