Abstract
Seeking effective neural networks is a critical and practical field in deep learning. Besides designing the depth, type of convolution, normalization, and nonlinearities, the topological connectivity of neural networks is also important. Previous principles of rule-based modular design simplify the difficulty of building an effective architecture, but constrain the possible topologies in limited spaces. In this paper, we attempt to optimize the connectivity in neural networks. We propose a topological perspective to represent a network into a complete graph for analysis, where nodes carry out aggregation and transformation of features, and edges determine the flow of information. By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner. We further attach auxiliary sparsity constraint to the distribution of connectedness, which promotes the learned topology focus on critical connections. This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks. Quantitative results of experiments reflect the learned connectivity is superior to traditional rule-based ones, such as random, residual and complete. In addition, it obtains significant improvements in image classification and object detection without introducing excessive computation burden.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
All of our experiments were performed using NVIDIA Tesla V100 GPUs with our implementation in PyTorch [25].
- 2.
References
Ahmed, K., Torresani, L.: Maskconnect: connectivity learning by gradient descent. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 349–365 (2018)
Bender, G., Kindermans, P.J., Zoph, B., Vasudevan, V., Le, Q.: Understanding and simplifying one-shot architecture search. In: International Conference on Machine Learning, pp. 550–559 (2018)
Dai, J., et al.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764–773 (2017)
DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. ar**v preprint ar**v:1708.04552 (2017)
Ghiasi, G., Lin, T.Y., Le, Q.V.: NAS-FPN: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7036–7045 (2019)
Girshick, R., Radosavovic, I., Gkioxari, G., Dollár, P., He, K.: Detectron (2018)
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315–323 (2011)
Guo, Z., et al.: Single path one-shot neural architecture search with uniform sampling. ar**v preprint ar**v:1904.00420 (2019)
Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems, pp. 1135–1143 (2015)
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)
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. ar**v preprint ar**v:1207.0580 (2012)
Howard, A., et al.: Searching for mobilenetv3. ar**v preprint ar**v:1905.02244 (2019)
Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. ar**v preprint ar**v:1704.04861 (2017)
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)
Huang, Z., Wang, N.: Data-driven sparse structure selection for deep neural networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 304–320 (2018)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
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_48
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)
Liu, H., Simonyan, K., Yang, Y.: Darts: differentiable architecture search. ar**v preprint ar**v:1806.09055 (2018)
Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. ar**v preprint ar**v:1608.03983 (2016)
Luo, P., Ren, J., Peng, Z., Zhang, R., Li, J.: Differentiable learning-to-normalize via switchable normalization. ar**v preprint ar**v:1806.10779 (2018)
Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: Proc. ICML, vol. 30, p. 3 (2013)
Paszke, A., et al.: Automatic differentiation in pytorch (2017)
Pérez-Rúa, J.M., Baccouche, M., Pateux, S.: Efficient progressive neural architecture search. ar**v preprint ar**v:1808.00391 (2018)
Ramachandran, P., Zoph, B., Le, Q.V.: Searching for activation functions. ar**v preprint ar**v:1710.05941 (2017)
Rauschecker, J.: Neuronal mechanisms of developmental plasticity in the cat’s visual system. Hum. Neurobiol. 3(2), 109–114 (1984)
Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4780–4789 (2019)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)
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)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. ar**v preprint ar**v:1409.1556 (2014)
Srivastava, R.K., Greff, K., Schmidhuber, J.: Highway networks. ar**v preprint ar**v:1505.00387 (2015)
Sun, K., et al.: High-resolution representations for labeling pixels and regions. ar**v preprint ar**v:1904.04514 (2019)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI conference on artificial intelligence (2017)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Tan, M., et al.: Mnasnet: platform-aware neural architecture search for mobile. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2820–2828 (2019)
Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks. ar**v preprint ar**v:1905.11946 (2019)
Tang, Z., Peng, X., Geng, S., Wu, L., Zhang, S., Metaxas, D.: Quantized densely connected u-nets for efficient landmark localization. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 339–354 (2018)
Veit, A., Wilber, M.J., Belongie, S.J.: Residual networks behave like ensembles of relatively shallow networks. In: NIPS, pp. 550–558 (2016)
Venables, W.N., Ripley, B.D.: Modern Applied Statistics with S-PLUS. Springer Science & Business Media, Berlin (2013)
Weinberger, K., Dasgupta, A., Langford, J., Smola, A., Attenberg, J.: Feature hashing for large scale multitask learning. In: Proceedings of the 26th annual international conference on machine learning. pp. 1113–1120 (2009)
Wu, Y., He, K.: Group normalization. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3–19 (2018)
**e, S., Kirillov, A., Girshick, R., He, K.: Exploring randomly wired neural networks for image recognition. ar**v preprint ar**v:1904.01569 (2019)
Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848–6856 (2018)
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)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Yuan, K., Li, Q., Shao, J., Yan, J. (2020). Learning Connectivity of Neural Networks from a Topological Perspective. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12366. Springer, Cham. https://doi.org/10.1007/978-3-030-58589-1_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-58589-1_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58588-4
Online ISBN: 978-3-030-58589-1
eBook Packages: Computer ScienceComputer Science (R0)