Active learning literature
This page is here to collect summaries of papers that focus on active learning. The idea is to share knowledge on recent developments in active learning.
If you've read a paper recently, write a little summary in markdown, put it in
the folder docs/research/literature
and make a pull request. You can even do all of
that right in the Github web UI!
The theory behind Bayesian active learning
In this document, we keep a list of the papers to get you started in Bayesian deep learning and Bayesian active learning.
We hope to include a summary for each of then in the future, but for now we have this list with some notes.
How to estimate uncertainty in Deep Learning networks
 Excellent tutorial from AGW on Bayesian Deep Learning
 This is inspired by his publication Bayesian Deep Learning and a Probabilistic Perspective of Generalization
 Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning (Gal and Ghahramani, 2016)
 This describes MonteCarlo Dropout, a way to estimate uncertainty through stochastic dropout at test time
 Bayesian Uncertainty Estimation for Batch Normalized Deep Networks (Teye et al. 2018)
 This describes MonteCarlo BatchNorm, a way to estimate uncertainty through random batch norm parameters at test time
 Bayesian Deep Learning and a Probabilistic Perspective of Generalization (Gordon Wilson and Izmailov, 2020)
 Presentation of multiSWAG a mix between VI and Ensembles.
 Advances in Variational inference (Zhang et al, 2018)
 Gives a quick introduction to VI and the most recent advances.
 A Simple Baseline for Bayesian Uncertainty in Deep Learning (Maddox et al. 2019)
 Presents SWAG, an easy way to create ensembles.
Bayesian active learning
 Deep Bayesian Active Learning with Image Data (Gal and Islam and Ghahramani, 2017)
 Fundamental paper on how to do Bayesian active learning. A must read.
 Sampling bias in active learning (Dasgupta 2009)

Presents sampling bias and how to solve it by combining heuristics and random selection.

Bayesian Active Learning for Classification and Preference Learning (Houlsby et al. 2011)
 Fundamental paper on one of the main heuristic BALD.
Bayesian active learning on NLP
 Deep Bayesian Active Learning for Natural Language Processing: Results of a LargeScale Empirical Study (Siddhant and Lipton, 2018)
 Experimental paper on how to use Bayesian active learning on NLP tasks.