Efficient Graph-Based Active Learning with Probit Likelihood via Gaussian Approximations

Abstract

We present a novel adaptation of active learning to graph-based semi-supervised learning (SSL) under non-Gaussian Bayesian models. We present an approximation of non-Gaussian distributions to adapt previously Gaussian-based acquisition functions to these more general cases. We develop an efficient rank-one update for applying "look-ahead" based methods as well as model retraining. We also introduce a novel "model change" acquisition function based on these approximations that further expands the available collection of active learning acquisition functions for such methods.

Accepted in ICML Workshop on Real World Experiment Design and Active Learning 2020

References in corpus (6)

• Bayesian Active Learning for Classification and Preference Learning
• Graph-Based Active Learning: A New Look at Expected Error Minimization
• Diffusion-based Deep Active Learning
• Consistency of semi-supervised learning algorithms on graphs: Probit and one-hot methods
• Minimum-Margin Active Learning
• Uncertainty quantification in graph-based classification of high dimensional data

Cited by in corpus (1)

• Model-Change Active Learning in Graph-Based Semi-Supervised Learning