CoChat

The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.

Compressing RNNs to Kilobyte Budget for IoT Devices Using Kronecker Products

Thakker, Urmish, Fedorov, Igor, Zhou, Chu, Gope, Dibakar, Mattina, Matthew, Dasika, Ganesh, Beu, Jesse · 2021 · ACM Journal on Emerging Technologies in Computing Systems

Abstract

Micro-controllers (MCUs) make up most of the processors in the world with widespread applicability from automobile to medical devices. The Internet of Things promises to enable these resource-constrained MCUs with machine learning algorithms to provide always-on intelligence. Many Internet of Things applications consume time-series data that are naturally suitable for recurrent neural networks (RNNs) like LSTMs and GRUs. However, RNNs can be large and difficult to deploy on these devices, as they have few kilobytes of memory. As a result, there is a need for compression techniques that can significantly compress RNNs without negatively impacting task accuracy. This article introduces a method to compress RNNs for resource-constrained environments using the Kronecker product (KP). KPs can compress RNN layers by 16× to 38× with minimal accuracy loss. By quantizing the resulting models to 8 bits, we further push the compression factor to 50×. We compare KP with other state-of-the-art compression techniques across seven benchmarks spanning five different applications and show that KP can beat the task accuracy achieved by other techniques by a large margin while simultaneously improving the inference runtime. Sometimes the KP compression mechanism can introduce an accuracy loss. We develop a hybrid KP approach to mitigate this. Our hybrid KP algorithm provides fine-grained control over the compression ratio, enabling us to regain accuracy lost during compression by adding a small…

Overview

Integrity signals

Registry

Crossref · 10.1145/3440016

Cites

37 of 37 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Show all 37 references

Research works printed but not linked: 25

  1. Martín Abadi , Ashish Agarwal , Paul Barham , Eugene Brevdo , Zhifeng Chen , Craig Citro , Greg S. Corrado , et al . 2015 . TensorFlow: Large- Scale Machine Learning on Heterogeneous Systems. Retrieved June 1, 2021 from https://www.tensorflow.org/. (Software available from tensorflow.org.) Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, et al. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Retrieved June 1, 2021 from https://www.tensorflow.org/. (Software available from tensorflow.org.)
  2. Colby R. Banbury , Vijay Janapa Reddi , Max Lam, William Fu, Amin Fazel, Jeremy Holleman, Xinyuan Huang, et al. 2020 . Benchmarking TinyML systems: Challenges and direction. arxiv:cs.PF/2003.04821. Colby R. Banbury, Vijay Janapa Reddi, Max Lam, William Fu, Amin Fazel, Jeremy Holleman, Xinyuan Huang, et al. 2020. Benchmarking TinyML systems: Challenges and direction. arxiv:cs.PF/2003.04821.
  3. Giuseppe Giovanni Calvi , Ahmad Moniri , Mahmoud Mahfouz , Zeyang Yu , Qibin Zhao , and Danilo P . Mandic . 2019 . Tucker tensor layer in fully connected neural networks. arxiv:1903.06133. Giuseppe Giovanni Calvi, Ahmad Moniri, Mahmoud Mahfouz, Zeyang Yu, Qibin Zhao, and Danilo P. Mandic. 2019. Tucker tensor layer in fully connected neural networks. arxiv:1903.06133. · arXiv
  4. 10.5555/3294771.3294792 · doi:10.5555/3294771.3294792
  5. 10.5555/2999792.2999852 · doi:10.5555/2999792.2999852
  6. 10.5555/3086952 · doi:10.5555/3086952
  7. Gael Guennebau and Benoit Jacob . 2009 . Eigen Library . Retrieved December 21, 2018 from http://eigen.tuxfamily.org/. Gael Guennebau and Benoit Jacob. 2009. Eigen Library. Retrieved December 21, 2018 from http://eigen.tuxfamily.org/.
  8. 10.5555/3060832.3060835 · doi:10.5555/3060832.3060835
  9. Song Han , Huizi Mao , and William J. Dally . 2016. Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding . In Proceedings of the International Conference on Learning Representations (ICLR’16) . Song Han, Huizi Mao, and William J. Dally. 2016. Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. In Proceedings of the International Conference on Learning Representations (ICLR’16).
  10. Qinyao He He Wen Shuchang Zhou Yuxin Wu Cong Yao Xinyu Zhou and Yuheng Zou. 2016. Effective quantization methods for recurrent neural networks. arxiv:1611.10176. Qinyao He He Wen Shuchang Zhou Yuxin Wu Cong Yao Xinyu Zhou and Yuheng Zou. 2016. Effective quantization methods for recurrent neural networks. arxiv:1611.10176. · arXiv
  11. Qinyao He He Wen Shuchang Zhou Yuxin Wu Cong Yao Xinyu Zhou and Yuheng Zou. 2016. Effective quantization methods for recurrent neural networks. arxiv:1611.10176. Qinyao He He Wen Shuchang Zhou Yuxin Wu Cong Yao Xinyu Zhou and Yuheng Zou. 2016. Effective quantization methods for recurrent neural networks. arxiv:1611.10176. · arXiv
  12. 10.5555/3122009.3242044 · doi:10.5555/3122009.3242044
  13. 10.5555/3305381.3305581 · doi:10.5555/3305381.3305581
  14. 10.5555/3327546.3327577 · doi:10.5555/3327546.3327577
  15. 10.5555/1062366 · doi:10.5555/1062366
  16. Zhouhan Lin Matthieu Courbariaux Roland Memisevic and Yoshua Bengio. 2015. Neural networks with few multiplications. arxiv:1510.03009. https://doi.org/10.1109/5.726791 · DOI · Paper page
  17. Christos Louizos , Max Welling , and Diederik P . Kingma . 2017 . Learning sparse neural networks through regularization. arxiv:1712.01312. Christos Louizos, Max Welling, and Diederik P. Kingma. 2017. Learning sparse neural networks through regularization. arxiv:1712.01312. · arXiv
  18. Sharan Narang , Eric Undersander , and Gregory F . Diamos . 2017 . Block-sparse recurrent neural networks. arxiv:1711.02782. Sharan Narang, Eric Undersander, and Gregory F. Diamos. 2017. Block-sparse recurrent neural networks. arxiv:1711.02782. · arXiv
  19. 10.5555/3295222.3295422 · doi:10.5555/3295222.3295422
  20. 10.5555/2969442.2969584 · doi:10.5555/2969442.2969584
  21. 10.5555/3327546.3327580 · doi:10.5555/3327546.3327580
  22. Vincent Vanhoucke , Andrew Senior , and Mark Z. Mao . 2011. Improving the speed of neural networks on CPUs . In Proceedings of theDeep Learning and Unsupervised Feature Learning Workshop (NIPS’11) . Vincent Vanhoucke, Andrew Senior, and Mark Z. Mao. 2011. Improving the speed of neural networks on CPUs. In Proceedings of theDeep Learning and Unsupervised Feature Learning Workshop (NIPS’11).
  23. 10.5555/3157382.3157643 · doi:10.5555/3157382.3157643
  24. Jiong Zhang , Qi Lei , and Inderjit S . Dhillon . 2018 . Stabilizing gradients for deep neural networks via efficient SVD parameterization. arxiv:1803.09327. Jiong Zhang, Qi Lei, and Inderjit S. Dhillon. 2018. Stabilizing gradients for deep neural networks via efficient SVD parameterization. arxiv:1803.09327. · arXiv
  25. Yundong Zhang , Naveen Suda , Liangzhen Lai , and Vikas Chandra . 2017 . Hello Edge: Keyword spotting on microcontrollers. arxiv:1711.07128. Yundong Zhang, Naveen Suda, Liangzhen Lai, and Vikas Chandra. 2017. Hello Edge: Keyword spotting on microcontrollers. arxiv:1711.07128. · arXiv

Cited by

See all 8

Metadata

Authors
Thakker, U., Fedorov, I., Zhou, C., Gope, D., Mattina, M., Dasika, G., & Beu, J.
Affiliations
  • Arm ML Research Lab, Austin, TX
  • AMD Research, Austin, TX
  • Arm ML Research Lab, Boston, MA
Venue
ACM Journal on Emerging Technologies in Computing Systems
Published
2021-07-14
Volume
17
Issue
4
Pages
1-18
ISSN
  • 1550-4832 (ISSN-L)
  • 1550-4840
OpenAlex
W3180864037
Cited by
8
References
37
Citations by year
2025: 2 · 2024: 2 · 2023: 2 · 2022: 1 · 2021: 1
FWCI
0.54
Type
journal article
Language
en
Open access
closed
Locations
ACM Journal on Emerging Technologies in Computing Systems (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
  • Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
Keywords
Kronecker product, Internet of Things, microcontroller, resource-constrained devices, 8-bit quantization, LSTM, GRU, hybrid compression, inference runtime, model size reduction, time series forecasting

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Compressing RNNs to Kilobyte Budget for IoT Devices Using Kronecker Products. https://app.cochat.ai/papers/10.1145/3440016
The paper
Thakker, U., Fedorov, I., Zhou, C., Gope, D., Mattina, M., Dasika, G., & Beu, J. (2021). Compressing RNNs to Kilobyte Budget for IoT Devices Using Kronecker Products. ACM Journal on Emerging Technologies in Computing Systems. https://doi.org/10.1145/3440016

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.