An Unbiased Risk Estimator for Learning with Augmented Classes

10/21/2019
by   Yu-Jie Zhang, et al.
31

In this paper, we study the problem of learning with augmented classes (LAC), where new classes that do not appear in the training dataset might emerge in the testing phase. The mixture of known classes and new classes in the testing distribution makes the LAC problem quite challenging. Our discovery is that by exploiting cheap and vast unlabeled data, the testing distribution can be estimated in the training stage, which paves us a way to develop algorithms with nice statistical properties. Specifically, we propose an unbiased risk estimator over the testing distribution for the LAC problem, and further develop an efficient algorithm to perform the empirical risk minimization. Both asymptotic and non-asymptotic analyses are provided as theoretical guarantees. The efficacy of the proposed algorithm is also confirmed by experiments.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/27/2022

Learning from Positive and Unlabeled Data with Augmented Classes

Positive Unlabeled (PU) learning aims to learn a binary classifier from ...
research
11/19/2022

Complementary Labels Learning with Augmented Classes

Complementary Labels Learning (CLL) arises in many real-world tasks such...
research
03/02/2017

Positive-Unlabeled Learning with Non-Negative Risk Estimator

From only positive (P) and unlabeled (U) data, a binary classifier could...
research
08/31/2018

On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data

Empirical risk minimization (ERM), with proper loss function and regular...
research
04/26/2019

Classification from Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization

Pairwise similarities and dissimilarities between data points might be e...
research
07/05/2022

Adapting to Online Label Shift with Provable Guarantees

The standard supervised learning paradigm works effectively when trainin...
research
06/07/2022

Towards Bridging Algorithm and Theory for Unbiased Recommendation

This work studies the problem of learning unbiased algorithms from biase...

Please sign up or login with your details

Forgot password? Click here to reset