Advertisement

CATCH: Context-Based Meta Reinforcement Learning for Transferrable Architecture Search

Conference paper
  • 644 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12364)

Abstract

Neural Architecture Search (NAS) achieved many breakthroughs in recent years. In spite of its remarkable progress, many algorithms are restricted to particular search spaces. They also lack efficient mechanisms to reuse knowledge when confronting multiple tasks. These challenges preclude their applicability, and motivate our proposal of CATCH, a novel Context-bAsed meTa reinforcement learning (RL) algorithm for transferrable arChitecture searcH. The combination of meta-learning and RL allows CATCH to efficiently adapt to new tasks while being agnostic to search spaces. CATCH utilizes a probabilistic encoder to encode task properties into latent context variables, which then guide CATCH’s controller to quickly “catch” top-performing networks. The contexts also assist a network evaluator in filtering inferior candidates and speed up learning. Extensive experiments demonstrate CATCH’s universality and search efficiency over many other widely-recognized algorithms. It is also capable of handling cross-domain architecture search as competitive networks on ImageNet, COCO, and Cityscapes are identified. This is the first work to our knowledge that proposes an efficient transferrable NAS solution while maintaining robustness across various settings.

Keywords

Neural architecture search Meta reinforcement learning 

Supplementary material

504475_1_En_12_MOESM1_ESM.pdf (478 kb)
Supplementary material 1 (pdf 477 KB)

References

  1. 1.
    Alemi, A.A., Fischer, I., Dillon, J.V., Murphy, K.: Deep variational information bottleneck. arXiv preprint arXiv:1612.00410 (2016)
  2. 2.
    Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13(Feb), 281–305 (2012)MathSciNetzbMATHGoogle Scholar
  3. 3.
    Bergstra, J., Yamins, D., Cox, D.: Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures. In: International Conference on Machine Learning, pp. 115–123 (2013)Google Scholar
  4. 4.
    Bergstra, J.S., Bardenet, R., Bengio, Y., Kégl, B.: Algorithms for hyper-parameter optimization. In: Advances in Neural Information Processing Systems, pp. 2546–2554 (2011)Google Scholar
  5. 5.
    Chen, L.C., et al.: Searching for efficient multi-scale architectures for dense image prediction. In: Advances in Neural Information Processing Systems, pp. 8699–8710 (2018)Google Scholar
  6. 6.
    Chen, L.C., et al.: Searching for efficient multi-scale architectures for dense image prediction. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31, pp. 8699–8710. Curran Associates Inc., Red Hook (2018)Google Scholar
  7. 7.
    Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: The European Conference on Computer Vision (ECCV) (2018)Google Scholar
  8. 8.
    Chen, Y., Yang, T., Zhang, X., Meng, G., Pan, C., Sun, J.: Detnas: Neural architecture search on object detection. arXiv preprint arXiv:1903.10979 (2019)
  9. 9.
    Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)Google Scholar
  10. 10.
    Deng,J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)Google Scholar
  11. 11.
    Dong, X., Yang, Y.: One-shot neural architecture search via self-evaluated template network. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3681–3690 (2019)Google Scholar
  12. 12.
    Dong, X., Yang, Y.: Searching for a robust neural architecture in four gpu hours. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1761–1770 (2019)Google Scholar
  13. 13.
    Dong, X., Yang, Y.: Nas-bench-201: extending the scope of reproducible neural architecture search. arXiv preprint arXiv:2001.00326 (2020)
  14. 14.
    Elsken, T., Metzen, J.H., Hutter, F.: Efficient multi-objective neural architecture search via lamarckian evolution. arXiv preprint arXiv:1804.09081 (2018)
  15. 15.
    Elsken, T., Staffler, B., Metzen, J., Hutter, F.: Meta-learning of neural architectures for few-shot learning. arXiv preprint arXiv:1911.11090 (2019)
  16. 16.
    Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. arXiv preprint arXiv:1703.03400 (2017)
  17. 17.
    Fu, J., et al.: Dual attention network for scene segmentation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)Google Scholar
  18. 18.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)Google Scholar
  19. 19.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  20. 20.
    Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)Google Scholar
  21. 21.
    Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: Ccnet: criss-cross attention for semantic segmentation. In: The IEEE International Conference on Computer Vision (ICCV) (2019)Google Scholar
  22. 22.
    Huber, P.J.: Robust estimation of a location parameter. In: Kotz, S., Johnson, N.L. (eds.) Breakthroughs in Statistics. Springer Series in Statistics (Perspectives in Statistics), pp. 492–518. Springer, New York (1992).  https://doi.org/10.1007/978-1-4612-4380-9_35CrossRefGoogle Scholar
  23. 23.
    Kim, J., et al.: Auto-meta: Automated gradient based meta learner search. arXiv preprint arXiv:1806.06927 (2018)
  24. 24.
    Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)
  25. 25.
    Lan, L., Li, Z., Guan, X., Wang, P.: Meta reinforcement learning with task embedding and shared policy. arXiv preprint arXiv:1905.06527 (2019)
  26. 26.
    Li, L., Talwalkar, A.: Random search and reproducibility for neural architecture search. arXiv preprint arXiv:1902.07638 (2019)
  27. 27.
    Li, Z., Zhou, F., Chen, F., Li, H.: Meta-sgd: learning to learn quickly for few-shot learning. arXiv preprint arXiv:1707.09835 (2017)
  28. 28.
    Lian, D., et al.: Towards fast adaptation of neural architectures with meta learning. In: International Conference on Learning Representations (2020)Google Scholar
  29. 29.
    Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)Google Scholar
  30. 30.
    Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10602-1_48CrossRefGoogle Scholar
  31. 31.
    Liu, B., et al.: Autofis: Automatic feature interaction selection in factorization models for click-through rate prediction. arXiv preprint arXiv:2003.11235 (2020)
  32. 32.
    Liu, C., et al.: Auto-deeplab: hierarchical neural architecture search for semantic image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 82–92 (2019)Google Scholar
  33. 33.
    Liu, H., Simonyan, K., Yang, Y.: Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)
  34. 34.
    Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)
  35. 35.
    Negrinho, R., Gordon, G.: Deeparchitect: Automatically designing and training deep architectures. arXiv preprint arXiv:1704.08792 (2017)
  36. 36.
    Pasunuru, R., Bansal, M.: Continual and multi-task architecture search. arXiv preprint arXiv:1906.05226 (2019)
  37. 37.
    Pham, H., Guan, M.Y., Zoph, B., Le, Q.V., Dean, J.: Efficient neural architecture search via parameter sharing. arXiv preprint arXiv:1802.03268 (2018)
  38. 38.
    Rakelly, K., Zhou, A., Quillen, D., Finn, C., Levine, S.: Efficient off-policy meta-reinforcement learning via probabilistic context variables. arXiv preprint arXiv:1903.08254 (2019)
  39. 39.
    Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Aging evolution for image classifier architecture search. In: AAAI Conference on Artificial Intelligence (2019)Google Scholar
  40. 40.
    Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4780–4789 (2019)Google Scholar
  41. 41.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)Google Scholar
  42. 42.
    Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)
  43. 43.
    Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
  44. 44.
    Shaw, A., Wei, W., Liu, W., Song, L., Dai, B.: Meta architecture search. In: Advances in Neural Information Processing Systems, pp. 11225–11235 (2019)Google Scholar
  45. 45.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)Google Scholar
  46. 46.
    Tan, M., et al.: Mnasnet: platform-aware neural architecture search for mobile. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)Google Scholar
  47. 47.
    Tan, M., Le, Q.V.: Efficientnet: Rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946 (2019)
  48. 48.
    Wang, J., Chen, K., Yang, S., Loy, C.C., Lin, D.: Region proposal by guided anchoring. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2965–2974 (2019)Google Scholar
  49. 49.
    Wang, N., Gao, Y., Chen, H., Wang, P., Tian, Z., Shen, C.: NAS-FCOS: fast neural architecture search for object detection. CoRR, abs/1906.04423 (2019)Google Scholar
  50. 50.
    Wang, P., et al.: Understanding convolution for semantic segmentation. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1451–1460 (2018)Google Scholar
  51. 51.
    Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3–4), 229–256 (1992)zbMATHGoogle Scholar
  52. 52.
    Wistuba, M.: Finding competitive network architectures within a day using uct. arXiv preprint arXiv:1712.07420 (2017)
  53. 53.
    Wong, C., Houlsby, N., Lu, Y., Gesmundo, A.: Transfer learning with neural automl. In: Advances in Neural Information Processing Systems, pp. 8356–8365 (2018)Google Scholar
  54. 54.
    Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492–1500 (2017)Google Scholar
  55. 55.
    Xu, H., Yao, L., Zhang, W., Liang, X., Li, Z.: Auto-FPN: automatic network architecture adaptation for object detection beyond classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6649–6658 (2019)Google Scholar
  56. 56.
    Yang, A., Esperança, P.M., Carlucci, F.F.: NAS evaluation is frustratingly hard. In: International Conference on Learning Representations (2020)Google Scholar
  57. 57.
    Yao, L., Xu, H., Zhang, W., Liang, X., Li, Z.: SM-NAS: structural-to-modular neural architecture search for object detection. arXiv preprint arXiv:1911.09929 (2019)
  58. 58.
    Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: Bisenet: bilateral segmentation network for real-time semantic segmentation. In: The European Conference on Computer Vision (ECCV) (2018)Google Scholar
  59. 59.
    Zhu, C., He, Y., Savvides, M.: Feature selective anchor-free module for single-shot object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 840–849 (2019)Google Scholar
  60. 60.
    Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)
  61. 61.
    Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697–8710 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.The University of Hong KongHong KongChina
  2. 2.Huawei Noah’s Ark LabHong KongChina
  3. 3.Sun Yat-sen UniversityGuangzhouChina
  4. 4.The Hong Kong University of Science and TechnologyHong KongChina

Personalised recommendations