Teaching to Teach by Structured Dark Knowledge

Ziliang Chen, Keze Wang, Liang Lin

Abstract: To educate hyper deep learners, \emph{Curriculum Learnings} (CLs) require either human heuristic participation or self-deciding the difficulties of training instances. These coaching manners are blind to the coherent structures among examples, categories, and tasks, which are pregnant with more knowledgeable curriculum-routed teachers. In this paper, we propose a general methodology \emph{Teaching to Teach} (T2T). T2T is facilitated by \emph{Structured Dark Knowledge} (SDK) that constitutes a communication protocol between structured knowledge prior and teaching strategies. On one hand, SDK adaptively extracts structured knowledge by selecting a training subset consistent with the previous teaching decisions. On the other hand, SDK teaches curriculum-agnostic teachers by transferring this knowledge to update their teaching policy. This virtuous cycle can be flexibly-deployed in most existing CL platforms and more importantly, very generic across various structured knowledge characteristics, e.g., diversity, complementarity, and causality. We evaluate T2T across different learners, teachers, and tasks, which significantly demonstrates that structured knowledge can be inherited by the teachers to further benefit learners' training.

Keywords: teaching to teach, dark knowledge, curriculum learning, teaching

TL;DR: We newly proposed ``teaching to teach, to educate a better teacher to teach a better student by introducing structured dark knowledge.