BAMLD: Bayesian Active Meta-Learning by Disagreement

10/19/2021
by   Ivana Nikoloska, et al.
0

Data-efficient learning algorithms are essential in many practical applications for which data collection and labeling is expensive or infeasible, e.g., for autonomous cars. To address this problem, meta-learning infers an inductive bias from a set of meta-training tasks in order to learn new, but related, task using a small number of samples. Most studies assume the meta-learner to have access to labeled data sets from a large number of tasks. In practice, one may have available only unlabeled data sets from the tasks, requiring a costly labeling procedure to be carried out before use in standard meta-learning schemes. To decrease the number of labeling requests for meta-training tasks, this paper introduces an information-theoretic active task selection mechanism which quantifies the epistemic uncertainty via disagreements among the predictions obtained under different inductive biases. We detail an instantiation for nonparametric methods based on Gaussian Process Regression, and report its empirical performance results that compare favourably against existing heuristic acquisition mechanisms.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/17/2020

Probabilistic Active Meta-Learning

Data-efficient learning algorithms are essential in many practical appli...
research
05/09/2020

Information-Theoretic Generalization Bounds for Meta-Learning and Applications

Meta-learning, or "learning to learn", refers to techniques that infer a...
research
10/21/2020

Conditional Mutual Information Bound for Meta Generalization Gap

Meta-learning infers an inductive bias—typically in the form of the hype...
research
01/05/2020

From Learning to Meta-Learning: Reduced Training Overhead and Complexity for Communication Systems

Machine learning methods adapt the parameters of a model, constrained to...
research
03/15/2021

How to distribute data across tasks for meta-learning?

Meta-learning models transfer the knowledge acquired from previous tasks...
research
03/20/2018

Meta Reinforcement Learning with Latent Variable Gaussian Processes

Data efficiency, i.e., learning from small data sets, is critical in man...
research
04/21/2021

Stateless Neural Meta-Learning using Second-Order Gradients

Deep learning typically requires large data sets and much compute power ...

Please sign up or login with your details

Forgot password? Click here to reset