Skip to main content
Springer Nature Link
Log in

Search-Time Efficient Device Constraints-Aware Neural Architecture Search

  • Conference paper
  • First Online:
Pattern Recognition and Machine Intelligence (PReMI 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14301))

  • 1091 Accesses

Abstract

Edge computing aims to enable edge devices, such as IoT devices, to process data locally instead of relying on the cloud. However, deep learning techniques like computer vision and natural language processing can be computationally expensive and memory-intensive. Creating manual architectures specialized for each device is infeasible due to their varying memory and computational constraints. To address these concerns, we automate the construction of task-specific deep learning architectures optimized for device constraints through Neural Architecture Search (NAS). We present DCA-NAS, a principled method of fast neural network architecture search that incorporates edge-device constraints such as model size and floating-point operations. It incorporates weight sharing and channel bottleneck techniques to speed up the search time. Based on our experiments, we see that DCA-NAS outperforms manual architectures for similar sized models and is comparable to popular mobile architectures on various image classification datasets like CIFAR-10, CIFAR-100, and Imagenet-1k. Experiments with search spaces—DARTS and NAS-Bench-201 show the generalization capabilities of DCA-NAS. On further evaluating our approach on Hardware-NAS-Bench, device-specific architectures with low inference latency and state-of-the-art performance were discovered.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    https://github.com/oshindutta/DCA-NAS.

References

  1. Abai, Z., Rajmalwar, N.: DenseNet models for tiny ImageNet classification (2020)

    Google Scholar 

  2. Cai, H., Gan, C., Wang, T., Zhang, Z., Han, S.: Once-for-all: train one network and specialize it for efficient deployment (2020). arXiv:1908.09791 [cs, stat]

  3. Cai, H., Zhu, L., Han, S.: ProxylessNAS: direct neural architecture search on target task and hardware (2019)

    Google Scholar 

  4. Chen, X., Hsieh, C.J.: Stabilizing differentiable architecture search via perturbation-based regularization. In: International Conference on Machine Learning, pp. 1554–1565. PMLR (2020)

    Google Scholar 

  5. Chen, X., Wang, R., Cheng, M., Tang, X., Hsieh, C.J.: DRNAS: Dirichlet neural architecture search. arXiv preprint arXiv:2006.10355 (2020)

  6. Chu, G., et al.: Discovering multi-hardware mobile models via architecture search. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3022–3031 (2021)

    Google Scholar 

  7. Ding, Y., et al.: NAP: neural architecture search with pruning. Neurocomputing 477, 85–95 (2022)

    Article  Google Scholar 

  8. Dong, X., Yang, Y.: Searching for a robust neural architecture in four GPU hours. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1761–1770 (2019)

    Google Scholar 

  9. Han, D., Kim, J., Kim, J.: Deep pyramidal residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5927–5935 (2017)

    Google Scholar 

  10. He, C., Ye, H., Shen, L., Zhang, T.: MileNAS: efficient neural architecture search via mixed-level reformulation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11993–12002 (2020)

    Google Scholar 

  11. He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1389–1397 (2017)

    Google Scholar 

  12. Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \(<\)0.5mb model size (2016)

    Google Scholar 

  13. Jiang, Q., Zhang, X., Chen, D., Do, M.N., Yeh, R.A.: EH-DNAS: end-to-end hardware-aware differentiable neural architecture search. arXiv:2111.12299 [cs] (2021)

  14. Jin, X., et al.: RC-DARTS: resource constrained differentiable architecture search. arXiv preprint arXiv:1912.12814 (2019)

  15. Kim, J.H., Choo, W., Song, H.O.: Puzzle mix: exploiting saliency and local statistics for optimal mixup (2020)

    Google Scholar 

  16. Li, G., Qian, G., Delgadillo, I.C., Müller, M., Thabet, A., Ghanem, B.: SGAS: sequential greedy architecture search (2020)

    Google Scholar 

  17. Lin, J., Chen, W.M., Lin, Y., Gan, C., Han, S., et al.: MCUNet: tiny deep learning on IoT devices. Adv. Neural. Inf. Process. Syst. 33, 11711–11722 (2020)

    Google Scholar 

  18. Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)

  19. Lyu, B., Yuan, H., Lu, L., Zhang, Y.: Resource-constrained neural architecture search on edge devices. IEEE Trans. Netw. Sci. Eng. 9(1), 134–142 (2022). https://doi.org/10.1109/TNSE.2021.3054583

    Article  Google Scholar 

  20. Ma, N., Zhang, X., Zheng, H.T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European conference on computer vision (ECCV), pp. 116–131 (2018)

    Google Scholar 

  21. Pham, H., Guan, M.Y., Zoph, B., Le, Q.V., Dean, J.: Efficient neural architecture search via parameter sharing. In: ICML (2018)

    Google Scholar 

  22. Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search (2019)

    Google Scholar 

  23. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)

    Google Scholar 

  24. Srivastava, A., Dutta, O., Gupta, J., Agarwal, S., Prathosh, A.P.: A variational information bottleneck based method to compress sequential networks for human action recognition. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 2745–2754 (2021)

    Google Scholar 

  25. Tan, M., et al.: platform-aware neural architecture search for mobile. In: 2019 IEEE CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2815–2823 (2019)

    Google Scholar 

  26. Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105–6114. PMLR (2019)

    Google Scholar 

  27. Wang, R., Cheng, M., Chen, X., Tang, X., Hsieh, C.J.: Rethinking architecture selection in differentiable NAS. arXiv preprint arXiv:2108.04392 (2021)

  28. Wistuba, M.: Deep learning architecture search by neuro-cell-based evolution with function-preserving mutations. In: Berlingerio, M., Bonchi, F., Gärtner, T., Hurley, N., Ifrim, G. (eds.) ECML PKDD 2018. LNCS (LNAI), vol. 11052, pp. 243–258. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-10928-8_15

    Chapter  Google Scholar 

  29. Wu, Y., et al.: Compiler-aware neural architecture search for on-mobile real-time super-resolution (2022). arXiv:2207.12577 [cs, eess]

  30. Xiao, H., Wang, Z., Zhu, Z., Zhou, J., Lu, J.: Shapley-NAS: discovering operation contribution for neural architecture search (2022). arXiv:2206.09811 [cs]

  31. Xie, S., Zheng, H., Liu, C., Lin, L.: SNAS: stochastic neural architecture search. In: International Conference on Learning Representations (2018)

    Google Scholar 

  32. Xiong, Y., Mehta, R., Singh, V.: Resource constrained neural network architecture search: will a submodularity assumption help? In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1901–1910 (2019)

    Google Scholar 

  33. Xu, Y., et al.: PC-DARTS: partial channel connections for memory-efficient architecture search. arXiv preprint arXiv:1907.05737 (2019)

  34. Yang, Y., You, S., Li, H., Wang, F., Qian, C., Lin, Z.: Towards improving the consistency, efficiency, and flexibility of differentiable neural architecture search. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6667–6676 (2021)

    Google Scholar 

  35. Zhou, H., Yang, M., Wang, J., Pan, W.: BayesNAS: a Bayesian approach for neural architecture search (2019)

    Google Scholar 

Download references

Acknowledgement

We thank the anonymous reviewers; Profs. Surendra Prasad and Brejesh Lall of IIT Delhi; and colleagues at Cadence India for their valuable feedback and inputs. This research is supported by funding from Cadence India; the first author is also supported by a fellowship from the Ministry of Education, India.

Author information

Authors and Affiliations

  1. Indian Institute of Technology, Delhi, India

    Oshin Dutta, Tanu Kanvar & Sumeet Agarwal

Authors
  1. Oshin Dutta
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tanu Kanvar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sumeet Agarwal
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Oshin Dutta .

Editor information

Editors and Affiliations

  1. Indian Statistical Institute, Kolkata, India

    Pradipta Maji

  2. Texas A&M University at Qatar, Doha, Qatar

    Tingwen Huang

  3. Indian Statistical Institute, Kolkata, West Bengal, India

    Nikhil R. Pal

  4. Indian Institute of Technology Jodhpur, Jodhpur, India

    Santanu Chaudhury

  5. Indian Statistical Institute, Kolkata, West Bengal, India

    Rajat K. De

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Dutta, O., Kanvar, T., Agarwal, S. (2023). Search-Time Efficient Device Constraints-Aware Neural Architecture Search. In: Maji, P., Huang, T., Pal, N.R., Chaudhury, S., De, R.K. (eds) Pattern Recognition and Machine Intelligence. PReMI 2023. Lecture Notes in Computer Science, vol 14301. Springer, Cham. https://doi.org/10.1007/978-3-031-45170-6_5

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-45170-6_5

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-45169-0

  • Online ISBN: 978-3-031-45170-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation