Covariate Distribution aware Meta-learning

Amrith Setlur, Saket Dingliwal, Barnabas Poczos

Student First Author: Yes

Keywords: meta-learning, few-shot learning, graphical model, bayesian

Abstract: Meta-learning has proven to be successful at few-shot learning across the regression, classification and reinforcement learning paradigms. Recent approaches have adopted Bayesian interpretations to improve gradient based meta-learners by quantifying the uncertainty of the post-adaptation estimates. Most of these works almost completely ignore the latent relationship between the covariate distribution (p(x)) of a task and the corresponding conditional distribution p(y|x). In this paper, we identify the need to explicitly model the meta-distribution over the task covariates in a hierarchical Bayesian framework. We begin by introducing a graphical model that explicitly leverages very few samples drawn from p(x) to better infer the posterior over the optimal parameters of the conditional distribution (p(y|x)) for each task. Based on this model we provide an inference strategy and a corresponding meta-algorithm that explicitly accounts for the meta-distribution over task covariates. Finally, we demonstrate the significant gains of our proposed algorithm on a synthetic regression dataset.

TL;DR: A probabilistic approach for meta-learning by modeling task covariate distributions in a hierarchical Bayesian framework.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/covariate-distribution-aware-meta-learning/code)