Contrastive Representation DistillationDownload PDF

Published: 20 Dec 2019, Last Modified: 22 Oct 2023ICLR 2020 Conference Blind SubmissionReaders: Everyone
Keywords: Knowledge Distillation, Representation Learning, Contrastive Learning, Mutual Information
TL;DR: Representation/knowledge distillation by maximizing mutual information between teacher and student
Abstract: Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from one sensory modality to a second, or ensembling a collection of models into a single estimator. Knowledge distillation, the standard approach to these problems, minimizes the KL divergence between the probabilistic outputs of a teacher and student network. We demonstrate that this objective ignores important structural knowledge of the teacher network. This motivates an alternative objective by which we train a student to capture significantly more information in the teacher's representation of the data. We formulate this objective as contrastive learning. Experiments demonstrate that our resulting new objective outperforms knowledge distillation on a variety of knowledge transfer tasks, including single model compression, ensemble distillation, and cross-modal transfer. When combined with knowledge distillation, our method sets a state of the art in many transfer tasks, sometimes even outperforming the teacher network.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 4 code implementations](
Original Pdf: pdf
8 Replies