Recent studies have indicated that foundation models, such as BERT and GPT, excel at
adapting to various downstream tasks. This adaptability has made them a dominant force in …

Visual analytics for machine learning has recently evolved as one of the most exciting areas
in the field of visualization. To better identify which research topics are promising and to …

Abstract Machine learning (ML) models are nowadays used in complex applications in
various domains, such as medicine, bioinformatics, and other sciences. Due to their black …

Microblogging is a popular online social network (OSN), which facilitates users to obtain and
share news and information. Nevertheless, it is filled with a huge number of social bots that …

Online social networks (OSNs) are a major component of societal digitalization. OSNs alter
how people communicate, make decisions, and form or change their beliefs, attitudes, and …

Semi-supervised learning (SSL) provides a way to improve the performance of prediction
models (eg, classifier) via the usage of unlabeled samples. An effective and widely used …

As training high-performance object detectors requires expensive bounding box
annotations, recent methods resort to free-available image captions. However, detectors …

Label quality issues, such as noisy labels and imbalanced class distributions, have negative
effects on model performance. Automatic reweighting methods identify problematic samples …

Constructing supervised machine learning models for real-world video analysis require
substantial labeled data, which is costly to acquire due to scarce domain expertise and …

Recent years have witnessed growing interest in understanding the sensitivity of machine
learning to training data characteristics. While researchers have claimed the benefits of …