Deep semi-supervised learning is a fast-growing field with a range of practical applications.
This paper provides a comprehensive survey on both fundamentals and recent advances in …

Abstract Machine learning is a field composed of various pillars. Traditionally, supervised
learning (SL), unsupervised learning (UL), and reinforcement learning (RL) are the …

Abstract Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of
machine learning systems. For instance, in autonomous driving, we would like the driving …

Fake news can rapidly spread through internet users and can deceive a large audience.
Due to those characteristics, they can have a direct impact on political and economic events …

Abstract Positive and Unlabeled Learning (PUL) uses unlabeled documents and a few
positive documents for retrieving a set of “interest” documents from a text collection. Usually …

Detecting anomalies or out-of-distribution (OOD) samples is critical for maintaining the
reliability and trustworthiness of machine learning systems. Recently, Large Language …

The digitalization of all areas of science, industry, and society has led to an unprecedented
flood of data. However, after the initial enthusiasm for the anticipated wealth of information …

Solar array management and photovoltaic (PV) fault detection is critical for optimal and
robust performance of solar plants. PV faults cause substantial power reduction along with …

Intelligent fault detection methods based on deep learning have been developed rapidly in
recent years. However, most of these methods are based on supervised learning which …

In the paper, we revisit the problem of class prior probability estimation with positive and
unlabelled data gathered in a single-sample scenario. The task is important as it is known …