Researchers are defining new types of interactions between humans and machine learning
algorithms generically called human-in-the-loop machine learning. Depending on who is in …

Curriculum learning (CL) is a training strategy that trains a machine learning model from
easier data to harder data, which imitates the meaningful learning order in human curricula …

The recently proposed FixMatch achieved state-of-the-art results on most semi-supervised
learning (SSL) benchmarks. However, like other modern SSL algorithms, FixMatch uses a …

Deep neural networks have been shown to be very powerful modeling tools for many
supervised learning tasks involving complex input patterns. However, they can also easily …

Recent deep networks are capable of memorizing the entire data even when the labels are
completely random. To overcome the overfitting on corrupted labels, we propose a novel …

Training machine learning models in a meaningful order, from the easy samples to the hard
ones, using curriculum learning can provide performance improvements over the standard …

Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks
in which the agent has only limited environmental feedback. Despite many advances over …

Mobile Edge Computing (MEC) is a promising technology to extend the diverse services to
the edge of Internet of Things (IoT) system. However, the static edge server deployment may …

Recent successes in learning-based image classification, however, heavily rely on the large
number of annotated training samples, which may require considerable human effort. In this …

Importance-weighted risk minimization is a key ingredient in many machine learning
algorithms for causal inference, domain adaptation, class imbalance, and off-policy …