Adaptive Negative Evidential Deep Learning for Open-set Semi-supervised Learning

by   Yang Yu, et al.
National University of Singapore
The Chinese University of Hong Kong

Semi-supervised learning (SSL) methods assume that labeled data, unlabeled data and test data are from the same distribution. Open-set semi-supervised learning (Open-set SSL) considers a more practical scenario, where unlabeled data and test data contain new categories (outliers) not observed in labeled data (inliers). Most previous works focused on outlier detection via binary classifiers, which suffer from insufficient scalability and inability to distinguish different types of uncertainty. In this paper, we propose a novel framework, Adaptive Negative Evidential Deep Learning (ANEDL) to tackle these limitations. Concretely, we first introduce evidential deep learning (EDL) as an outlier detector to quantify different types of uncertainty, and design different uncertainty metrics for self-training and inference. Furthermore, we propose a novel adaptive negative optimization strategy, making EDL more tailored to the unlabeled dataset containing both inliers and outliers. As demonstrated empirically, our proposed method outperforms existing state-of-the-art methods across four datasets.


page 3

page 7


OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers

Semi-supervised learning (SSL) is an effective means to leverage unlabel...

Prompt-driven efficient Open-set Semi-supervised Learning

Open-set semi-supervised learning (OSSL) has attracted growing interest,...

Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics

Self-training based semi-supervised learning algorithms have enabled the...

S2OSC: A Holistic Semi-Supervised Approach for Open Set Classification

Open set classification (OSC) tackles the problem of determining whether...

LitGen: Genetic Literature Recommendation Guided by Human Explanations

As genetic sequencing costs decrease, the lack of clinical interpretatio...

Please sign up or login with your details

Forgot password? Click here to reset