Advertisement

ProxyBNN: Learning Binarized Neural Networks via Proxy Matrices

Conference paper
  • 518 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12348)

Abstract

Training Binarized Neural Networks (BNNs) is challenging due to the discreteness. In order to efficiently optimize BNNs through backward propagations, real-valued auxiliary variables are commonly used to accumulate gradient updates. Those auxiliary variables are then directly quantized to binary weights in the forward pass, which brings about large quantization errors. In this paper, by introducing an appropriate proxy matrix, we reduce the weights quantization error while circumventing explicit binary regularizations on the full-precision auxiliary variables. Specifically, we regard pre-binarization weights as a linear combination of the basis vectors. The matrix composed of basis vectors is referred to as the proxy matrix, and auxiliary variables serve as the coefficients of this linear combination. We are the first to empirically identify and study the effectiveness of learning both basis and coefficients to construct the pre-binarization weights. This new proxy learning contributes to new leading performances on benchmark datasets.

Keywords

Binarized Neural Networks Proxy matrix 

Notes

Acknowledgement

This work was supported in part by National Natural Science Foundation of China (No.61972396, 61876182, 61906193), National Key Research and Development Program of China (No. 2019AAA0103402), the Strategic Priority Research Program of Chinese Academy of Science(No.XDB32050200), the Advance Research Program (No. 31511130301), and Jiangsu Frontier Technology Basic Research Project (No. BK20192004).

Supplementary material

504435_1_En_14_MOESM1_ESM.pdf (193 kb)
Supplementary material 1 (pdf 193 KB)

References

  1. 1.
    Alizadeh, M., Fernández-Marqués, J., Lane, N.D., Gal, Y.: A systematic study of binary neural networks’ optimisation. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=rJfUCoR5KX
  2. 2.
    Anderson, A.G., Berg, C.P.: The high-dimensional geometry of binary neural networks. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=B1IDRdeCW
  3. 3.
    Andoni, A., Indyk, P.: Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions. Commun. ACM 51(1), 117–122 (2008). http://doi.acm.org/10.1145/1327452.1327494
  4. 4.
    Bahou, A.A., Karunaratne, G., Andri, R., Cavigelli, L., Benini, L.: XNORBIN: A 95 top/s/w hardware accelerator for binary convolutional neural networks. In: 2018 IEEE Symposium in Low-Power and High-Speed Chips, COOL CHIPS 2018, Yokohama, Japan, 18–20 Apr 2018, pp. 1–3. IEEE Computer Society (2018). https://doi.org/10.1109/CoolChips.2018.8373076
  5. 5.
    Bethge, J., Yang, H., Bornstein, M., Meinel, C.: Back to simplicity: How to train accurate BNNs from scratch? CoRR abs/1906.08637 (2019). http://arxiv.org/abs/1906.08637
  6. 6.
    Bulat, A., Tzimiropoulos, G.: XNOR-Net++: Improved binary neural networks. In: British Machine Vision Conference, BMVC 2019 (2019)Google Scholar
  7. 7.
    Bulat, A., Tzimiropoulos, G., Kossaifi, J., Pantic, M.: Improved training of binary networks for human pose estimation and image recognition. CoRR abs/1904.05868 (2019). http://arxiv.org/abs/1904.05868
  8. 8.
    Cheng, J., Leng, C., Wu, J., Cui, H., Lu, H.: Fast and accurate image matching with cascade hashing for 3d reconstruction. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, USA, 23–28 Jun 2014, pp. 1–8 (2014). https://doi.org/10.1109/CVPR.2014.8
  9. 9.
    Courbariaux, M., Bengio, Y., David, J.: Binaryconnect: Training deep neural networks with binary weights during propagations. In: Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 7–12 Dec 2015, Montreal, Quebec, Canada, pp. 3123–3131 (2015). http://papers.nips.cc/paper/5647-binaryconnect-training-deep-neural-networks-with-binary-weights-during-propagations
  10. 10.
    Darabi, S., Belbahri, M., Courbariaux, M., Nia, V.P.: BNN+: improved binary network training. CoRR abs/1812.11800 (2018). http://arxiv.org/abs/1812.11800
  11. 11.
    Ding, R., Chin, T., Liu, Z., Marculescu, D.: Regularizing activation distribution for training binarized deep networks. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16–20 June 2019, pp. 11408–11417 (2019)Google Scholar
  12. 12.
    Gong, Y., Lazebnik, S., Gordo, A., Perronnin, F.: Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2916–2929 (2013). https://doi.org/10.1109/TPAMI.2012.193
  13. 13.
    Gu, J., et al.: Projection convolutional neural networks for 1-bit CNNs via discrete back propagation. In: The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, 27 Jan–1 Feb 2019, pp. 8344–8351 (2019). https://doi.org/10.1609/aaai.v33i01.33018344
  14. 14.
    Gu, J., et al.: Bayesian optimized 1-bit CNNs. In: IEEE Proceedings of the IEEE International Conference on Computer Vision ICCV 2019, Seoul, South Korea (2019)Google Scholar
  15. 15.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27–30 Jun 2016, pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90
  16. 16.
    He, X., Wang, P., Cheng, J.: K-nearest neighbors hashing. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, 16–20 Jun 2019, pp. 2839–2848 (2019). http://openaccess.thecvf.com/content_CVPR_2019/html/He_K-Nearest_Neighbors_Hashing_CVPR_2019_paper.html
  17. 17.
    Helwegen, K., Widdicombe, J., Geiger, L., Liu, Z., Cheng, K., Nusselder, R.: Latent weights do not exist: Rethinking binarized neural network optimization. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8–14 Dec 2019, Vancouver, BC, Canada, pp. 7531–7542 (2019). http://papers.nips.cc/paper/8971-latent-weights-do-not-exist-rethinking-binarized-neural-network-optimization
  18. 18.
    Hu, Q., Wang, P., Cheng, J.: From hashing to CNNs: Training binary weight networks via hashing. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, 2–7 Feb 2018, pp. 3247–3254 (2018). https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16466
  19. 19.
    Hu, Q., Wu, J., Bai, L., Zhang, Y., Cheng, J.: Fast k-means for large scale clustering. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, CIKM 2017, Singapore, 06–10 Nov 2017, pp. 2099–2102 (2017). https://doi.org/10.1145/3132847.3133091
  20. 20.
    Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks. In: Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 5–10 Dec 2016, Barcelona, Spain, pp. 4107–4115 (2016). http://papers.nips.cc/paper/6573-binarized-neural-networks
  21. 21.
    Ji, C., Psaltis, D.: Capacity of two-layer feedforward neural networks with binary weights. IEEE Trans. Inf. Theory 44(1), 256–268 (1998). https://doi.org/10.1109/18.651033
  22. 22.
    Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings (2015). http://arxiv.org/abs/1412.6980
  23. 23.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017). http://doi.acm.org/10.1145/3065386
  24. 24.
    Leng, C., Dou, Z., Li, H., Zhu, S., Jin, R.: Extremely low bit neural network: Squeeze the last bit out with ADMM. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, 2–7 Feb 2018, pp. 3466–3473 (2018). https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16767
  25. 25.
    Lin, X., Zhao, C., Pan, W.: Towards accurate binary convolutional neural network. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4–9 Dec 2017, Long Beach, CA, USA, pp. 345–353 (2017). http://papers.nips.cc/paper/6638-towards-accurate-binary-convolutional-neural-network
  26. 26.
    Lin, Z., Courbariaux, M., Memisevic, R., Bengio, Y.: Neural networks with few multiplications. In: 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, 2–4 May 2016, Conference Track Proceedings (2016). http://arxiv.org/abs/1510.03009
  27. 27.
    Liu, C., Ding, W., Hu, Y., Zhang, B., Liu, J., Guo, G.: GBCNs: Genetic binary convolutional networks for enhancing the performance of 1-bit DCNNs. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20) (February 2020)Google Scholar
  28. 28.
    Liu, Z., Wu, B., Luo, W., Yang, X., Liu, W., Cheng, K.: Bi-real net: Enhancing the performance of 1-bit CNNs with improved representational capability and advanced training algorithm. In: Computer Vision - ECCV 2018–15th European Conference, Munich, Germany, 8–14 Sept 2018, Proceedings, Part XV, pp. 747–763 (2018). https://doi.org/10.1007/978-3-030-01267-0_44
  29. 29.
    Martinez, B., Yang, J., Bulat, A., Tzimiropoulos, G.: Training binary neural networks with real-to-binary convolutions. In: International Conference on Learning Representations (2020). https://openreview.net/forum?id=BJg4NgBKvH
  30. 30.
    Mayoraz, E., Aviolat, F.: Constructive training methods for feedforward neural networks with binary weights. Int. J. Neural Syst. 7(2), 149–66 (1995)CrossRefGoogle Scholar
  31. 31.
    Mishra, A.K., Nurvitadhi, E., Cook, J.J., Marr, D.: WRPN: wide reduced-precision networks. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, 30 Apr–3 May 2018, Conference Track Proceedings (2018). https://openreview.net/forum?id=B1ZvaaeAZ
  32. 32.
    Oliveira, A.L., Sangiovanni-Vincentelli, A.L.: Learning complex Boolean functions: Algorithms and applications. In: Advances in Neural Information Processing Systems 6, [7th NIPS Conference, Denver, Colorado, USA, 1993], pp. 911–918 (1993). http://papers.nips.cc/paper/857-learning-complex-boolean-functions-algorithms-and-applications
  33. 33.
    Pagallo, G., Haussler, D.: Boolean feature discovery in empirical learning. Mach. Learn. 5, 71–99 (1990). https://doi.org/10.1007/BF00115895
  34. 34.
    Paszke, A., et al.: Pytorch: An imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8–14 Dec 2019, Vancouver, BC, Canada, pp. 8024–8035 (2019). http://papers.nips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library
  35. 35.
    Peters, J.W., Genewein, T., Welling, M.: Probabilistic binary neural networks (2019). https://openreview.net/forum?id=B1fysiAqK7
  36. 36.
    Qin, H., Gong, R., Liu, X., Wei, Z., Yu, F., Song, J.: IR-Net: Forward and backward information retention for highly accurate binary neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle Wastington, USA (June 2020)Google Scholar
  37. 37.
    Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: Imagenet classification using binary convolutional neural networks. In: Computer Vision - ECCV 2016–14th European Conference, Amsterdam, The Netherlands, 11–14 Oct 2016, Proceedings, Part IV, pp. 525–542 (2016). https://doi.org/10.1007/978-3-319-46493-0_32
  38. 38.
    Rublee, E., Rabaud, V., Konolige, K., Bradski, G.R.: ORB: An efficient alternative to SIFT or SURF. In: IEEE International Conference on Computer Vision, ICCV 2011, Barcelona, Spain, 6–13 Nov 2011, pp. 2564–2571 (2011). https://doi.org/10.1109/ICCV.2011.6126544
  39. 39.
    Santurkar, S., Tsipras, D., Ilyas, A., Madry, A.: How does batch normalization help optimization? In: Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3–8 Dec 2018, Montréal, Canada, pp. 2488–2498 (2018). http://papers.nips.cc/paper/7515-how-does-batch-normalization-help-optimization
  40. 40.
    Schonemann, P.H.: A generalized solution of the orthogonal procrustes problem. Psychometrika 31(1), 1–10 (1966)MathSciNetCrossRefGoogle Scholar
  41. 41.
    Shayer, O., Levi, D., Fetaya, E.: Learning discrete weights using the local reparameterization trick. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, 30 Apr–3 May 2018, Conference Track Proceedings. OpenReview.net (2018). https://openreview.net/forum?id=BySRH6CpW
  42. 42.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings (2015). http://arxiv.org/abs/1409.1556
  43. 43.
    Soudry, D., Hubara, I., Meir, R.: Expectation backpropagation: Parameter-free training of multilayer neural networks with continuous or discrete weights. In: Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 8–13 Dec 2014, Montreal, Quebec, Canada, pp. 963–971 (2014). http://papers.nips.cc/paper/5269-expectation-backpropagation-parameter-free-training-of-multilayer-neural-networks-with-continuous-or-discrete-weights
  44. 44.
    Soudry, D., Meir, R.: Mean field Bayes backpropagation: scalable training of multilayer neural networks with binary weights (2013)Google Scholar
  45. 45.
    Tang, W., Hua, G., Wang, L.: How to train a compact binary neural network with high accuracy? In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 4–9 Feb 2017, San Francisco, California, USA, pp. 2625–2631 (2017). http://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14619
  46. 46.
    Wang, P., He, X., Li, G., Zhao, T., Cheng, J.: Sparsity-inducing binarized neural networks. In: The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20) (February 2020)Google Scholar
  47. 47.
    Wen, Y., Zhang, K., Li, Z., Qiao, Y.: A discriminative feature learning approach for deep face recognition. In: Computer Vision-ECCV 2016–14th European Conference, Amsterdam, The Netherlands, 11–14 Oct 2016, Proceedings, Part VII, pp. 499–515 (2016). https://doi.org/10.1007/978-3-319-46478-7_31
  48. 48.
    Yang, J., et al.: Quantization networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach CA, USA (June 2019)Google Scholar
  49. 49.
    Yazdani, M.: Linear backprop in non-linear networks. In: Compact Deep Neural Network Representation with Industrial Applications Workshop, Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3–8 Dec 2018, Montréal, Canada (2018)Google Scholar
  50. 50.
    Zagoruyko, S., Komodakis, N.: Wide residual networks. In: Proceedings of the British Machine Vision Conference 2016, BMVC 2016, York, UK, 19–22 Sept 2016 (2016). http://www.bmva.org/bmvc/2016/papers/paper087/index.html
  51. 51.
    Zhao, T., He, X., Cheng, J., Hu, J.: Bitstream: Efficient computing architecture for real-time low-power inference of binary neural networks on CPUs. In: Boll, S., Lee, K.M., Luo, J., Zhu, W., Byun, H., Chen, C.W., Lienhart, R., Mei, T. (eds.) 2018 ACM Multimedia Conference on Multimedia Conference, MM 2018, Seoul, Republic of Korea, 22–26 Oct 2018, pp. 1545–1552. ACM (2018). https://doi.org/10.1145/3240508.3240673
  52. 52.
    Zhou, S., Ni, Z., Zhou, X., Wen, H., Wu, Y., Zou, Y.: DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients. CoRR abs/1606.06160 (2016). http://arxiv.org/abs/1606.06160

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.NLPR, Institute of AutomationChinese Academy of SciencesBeijingChina
  2. 2.School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijingChina
  3. 3.Center for Excellence in Brain Science and Intelligence TechnologyBeijingChina
  4. 4.Nanjing University of Information Science and TechnologyNanjingChina

Personalised recommendations