I will talk about multi-task learning methods and some recent works in deep learning.
In Machine Learning, we typically care about optimizing for a particular metric, but ignore the potential improvement by information coming from the training signals of related tasks. Multi-Task Learning (joint learning, learning to learn, learning with auxiliary tasks, etc.) is a hot area of machine learning where multiple tasks are solved at the same time. It has been used successfully across all applications of machine learning, from natural language processing to computer vision.