AutoReCon: Neural Architecture Search-based Reconstruction for Data-free Compression
This work addresses data-free compression for scenarios with privacy or transmission constraints, offering an incremental improvement by incorporating network engineering into reconstruction methods.
The paper tackles data-free compression, where the original training data is unavailable, by proposing AutoReCon, a neural architecture search-based method to automatically design generator architectures for reconstructing training datasets, which improves compression performance in experiments.
Data-free compression raises a new challenge because the original training dataset for a pre-trained model to be compressed is not available due to privacy or transmission issues. Thus, a common approach is to compute a reconstructed training dataset before compression. The current reconstruction methods compute the reconstructed training dataset with a generator by exploiting information from the pre-trained model. However, current reconstruction methods focus on extracting more information from the pre-trained model but do not leverage network engineering. This work is the first to consider network engineering as an approach to design the reconstruction method. Specifically, we propose the AutoReCon method, which is a neural architecture search-based reconstruction method. In the proposed AutoReCon method, the generator architecture is designed automatically given the pre-trained model for reconstruction. Experimental results show that using generators discovered by the AutoRecon method always improve the performance of data-free compression.