ELRT: Towards Efficient Low-Rank Training for Compact Neural Networks

Yang Sui, Miao Yin, Wanzhao Yang, Yu Gong, Jinqi Xiao, Huy Phan, Ding Ding, Xiaozhong Xu, Shan Liu, Zhenzhong Chen, Bo Yuan

Abstract: Low-rank compression, a popular model compression technique that produces compact convolutional neural networks (CNNs) with low rankness, has been well studied in the literature. On the other hand, low-rank training, as an alternative way to train low-rank CNNs from scratch, is little exploited yet. Unlike low-rank compression, low-rank training does not need pre-trained full-rank models and the entire training phase is always performed on the low-rank structure, bringing attractive benefits for practical applications. However, the existing low-rank training solutions are still very limited and do not demonstrate their effectiveness for training modern low-rank CNN models in the large-scale dataset from scratch. In this paper, we perform a systematic investigation on low-rank CNN training. By identifying the proper low-rank format and performance-improving strategy, we propose ELRT, an efficient low-rank training solution for high-accuracy high-compactness low-rank CNN models. Our extensive evaluation results for training various CNNs on different datasets demonstrate the effectiveness of ELRT.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning