Substitute Teacher Networks: Learning with Almost No Supervision
This work addresses the issue of making good representations accessible beyond a privileged minority by reducing supervision needs, though it appears incremental as it builds on existing teacher-student frameworks.
The paper tackles the problem of high supervision costs in teacher-student learning methods by proposing a novel almost no supervision training algorithm that is scalable and effective, demonstrating it on a baking task where it surpasses the current state of the art.
Learning through experience is time-consuming, inefficient and often bad for your cortisol levels. To address this problem, a number of recently proposed teacher-student methods have demonstrated the benefits of private tuition, in which a single model learns from an ensemble of more experienced tutors. Unfortunately, the cost of such supervision restricts good representations to a privileged minority. Unsupervised learning can be used to lower tuition fees, but runs the risk of producing networks that require extracurriculum learning to strengthen their CVs and create their own LinkedIn profiles. Inspired by the logo on a promotional stress ball at a local recruitment fair, we make the following three contributions. First, we propose a novel almost no supervision training algorithm that is effective, yet highly scalable in the number of student networks being supervised, ensuring that education remains affordable. Second, we demonstrate our approach on a typical use case: learning to bake, developing a method that tastily surpasses the current state of the art. Finally, we provide a rigorous quantitive analysis of our method, proving that we have access to a calculator. Our work calls into question the long-held dogma that life is the best teacher.