arXiv:1710.07535cs.LG
Data-Free Knowledge Distillation for Deep Neural Networks
Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
Abstract
Recent advances in model compression have provided procedures for compressing large neural networks to a fraction of their original size while retaining most if not all of their accuracy. However, all of these approaches rely on access to the original training set, which might not always be possible if the network to be compressed was trained on a very large dataset, or on a dataset whose release poses privacy or safety concerns as may be the case for biometrics tasks. We present a method for data-free knowledge distillation, which is able to compress deep neural networks trained on large-scale datasets to a fraction of their size leveraging only some extra metadata to be provided with a pretrained model release. We also explore different kinds of metadata that can be used with our method, and discuss tradeoffs involved in using each of them.
https://arxiv.org/abs/1711.09784 https://arxiv.org/abs/1708.01785 https://arxiv.org/abs/1710.00935 https://arxiv.org/abs/1702.04595 https://arxiv.org/abs/1801.01693 https://arxiv.org/abs/1503.02531 https://arxiv.org/abs/1712.03781 https://arxiv.org/abs/1710.07535…
sovok_xView on HNParent context