Complementary Labels Learning with Augmented Classes

TL;DR

This paper introduces a new learning setting called CLLAC where classifiers trained with complementary labels must also identify unseen augmented classes, using an unbiased risk estimator and demonstrating effectiveness on benchmarks.

Contribution

The paper proposes a novel CLLAC framework with an unbiased risk estimator and theoretical guarantees, addressing open-world scenarios in complementary labels learning.

Findings

The proposed method is effective on benchmark datasets.

The risk estimator is proven to be consistent.

Achieves optimal parametric convergence rate.

Abstract

Complementary Labels Learning (CLL) arises in many real-world tasks such as private questions classification and online learning, which aims to alleviate the annotation cost compared with standard supervised learning. Unfortunately, most previous CLL algorithms were in a stable environment rather than an open and dynamic scenarios, where data collected from unseen augmented classes in the training process might emerge in the testing phase. In this paper, we propose a novel problem setting called Complementary Labels Learning with Augmented Classes (CLLAC), which brings the challenge that classifiers trained by complementary labels should not only be able to classify the instances from observed classes accurately, but also recognize the instance from the Augmented Classes in the testing phase. Specifically, by using unlabeled data, we propose an unbiased estimator of classification risk for CLLAC, which is guaranteed to be provably consistent. Moreover, we provide generalization error bound for proposed method which shows that the optimal parametric convergence rate is achieved for estimation error. Finally, the experimental results on several benchmark datasets verify the effectiveness of the proposed method.