Oracle Teacher: Towards Better Knowledge Distillation

Knowledge distillation (KD), best known as an effective method for model compression, aims at transferring the knowledge of a bigger network (teacher) to a much smaller network (student). Conventional KD methods usually employ the teacher model trained in a supervised manner, where output labels are treated only as targets. Extending this supervised scheme further, we introduce a new type of teacher model for KD, namely Oracle Teacher, that utilizes the embeddings of both the source inputs and the output labels to extract a more accurate knowledge to be transferred to the student. One potential risk for the proposed approach is a trivial solution that the model's output directly copies the oracle input. In Oracle Teacher, we present a training scheme that can effectively prevent the trivial solution and thus enables utilizing both source inputs and oracle inputs for model training. Extensive experiments are conducted on three different sequence learning tasks: speech recognition, scene text recognition, and machine translation. From the experimental results, we empirically show that the proposed model improves the students across these tasks while achieving a considerable speed-up in the teacher model's training time.