Efficient Active Learning with Abstention

03/31/2022
by   Yinglun Zhu, et al.
0

The goal of active learning is to achieve the same accuracy achievable by passive learning, while using much fewer labels. Exponential savings in label complexity are provably guaranteed in very special cases, but fundamental lower bounds show that such improvements are impossible in general. This suggests a need to explore alternative goals for active learning. Learning with abstention is one such alternative. In this setting, the active learning algorithm may abstain from prediction in certain cases and incur an error that is marginally smaller than 1/2. We develop the first computationally efficient active learning algorithm with abstention. Furthermore, the algorithm is guaranteed to only abstain on hard examples (where the true label distribution is close to a fair coin), a novel property we term "proper abstention" that also leads to a host of other desirable characteristics. The option to abstain reduces the label complexity by an exponential factor, with no assumptions on the distribution, relative to passive learning algorithms and/or active learning that are not allowed to abstain. A key feature of the algorithm is that it avoids the undesirable "noise-seeking" behavior often seen in active learning. We also explore extensions that achieve constant label complexity and deal with model misspecification.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/08/2011

Activized Learning: Transforming Passive to Active with Improved Label Complexity

We study the theoretical advantages of active learning over passive lear...
research
10/15/2022

Active Learning with Neural Networks: Insights from Nonparametric Statistics

Deep neural networks have great representation power, but typically requ...
research
11/19/2013

Beating the Minimax Rate of Active Learning with Prior Knowledge

Active learning refers to the learning protocol where the learner is all...
research
12/07/2011

Active Learning of Halfspaces under a Margin Assumption

We derive and analyze a new, efficient, pool-based active learning algor...
research
07/08/2019

The Power of Comparisons for Actively Learning Linear Classifiers

In the world of big data, large but costly to label datasets dominate ma...
research
06/21/2021

Corruption Robust Active Learning

We conduct theoretical studies on streaming-based active learning for bi...
research
01/21/2013

A Linear Time Active Learning Algorithm for Link Classification -- Full Version --

We present very efficient active learning algorithms for link classifica...

Please sign up or login with your details

Forgot password? Click here to reset