An Overview of Multi-Task Learning for Deep Learning

Note: If you are looking for a review paper, this blog post is also available as an article on arXiv. In Machine Learning (ML), we typically care about optimizing for a particular metric, whether this is a score on a certain benchmark or a business KPI. In order to do this, we generally train a single model or an ensemble of models to perform our desired task. While we can generally achieve acceptable performance this way, by being laser-focused on our single task, we ignore information that might help us do even better on the metric we care about. Specifically, this information comes from the training signals of related tasks. By sharing representations between related tasks, we can enable our model to generalize better on our original task. This approach is called Multi-Task Learning (MTL) and will be the topic of this blog post. Multi-task learning has been used successfully across all applications of machine learning, from natural language processing [1] and speech recognition [2] to computer vision [3] and drug discovery [4]. MTL comes in many guises: joint learning, learning to learn, and learning with auxiliary tasks are only some names that have been used to refer to it. Generally, as soon as you find yourself optimizing more than one loss function, you are effectively doing multi-task learning (in contrast to single-task learning).