Machine Learning and Data Classification
This cluster of papers focuses on the challenges and techniques for learning with noisy labels in machine learning, including methods for hyperparameter optimization, instance selection, robust learning, and automated machine learning. It also explores the use of meta-learning and deep neural networks in handling noisy label problems, particularly in the context of classification tasks and learning from positive and unlabeled data.
Papers listed on taxonomy pages are the top few works per node from the OpenAlex snapshot. That list is not exhaustive and is not an endorsement. The topic map and the journal registry remain separate: there is still no authoritative topic-to-venue or topic-to-organization edge. Search is a lexical lookup, not a claim that a venue publishes a topic.