Abstract
Neural networks are traditionally represented in terms of their weights. A key property of this representation is that there are multiple representations of a network which can be obtained by permuting the order of the neurons. These representations are generally not compatible between networks, making recombination a challenge for two arbitrary neural networks - an issue known as the “permutation problem” in neuroevolution. This paper proposes an indirect encoding in which a neural network is represented in terms of interactions between neurons rather than explicit weights, and which works for both fully connected and convolutional networks. In addition to reducing the number of free parameters, this encoding is agnostic to the ordering of neurons, bypassing a key problem for direct weight-based representation. This allows us to transplant individual neurons and layers into another network without accounting for the specific ordering of neurons. We show through experiments on the MNIST and CIFAR-10 datasets that this method is capable of representing networks which achieve comparable performance to direct weight representation, and that combining networks this way preserves a larger degree of performance than through direct weight transfer.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bacciu, D., Mandic, D.P.: Tensor decompositions in deep learning. In: Computational Intelligence, p. 10 (2020)
Chen, X., Cheng, X., Mallat, S.: Unsupervised Deep HAAR Scattering on Graphs. In: Advances in Neural Information Processing System, vol. 27. Curran Associates, Inc. (2014)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1800–1807. IEEE, Honolulu, HI, July 2017. https://doi.org/10.1109/CVPR.2017.195
Coleman, C., et al.: DAWNBench: an end-to-end deep learning benchmark and competition. In: NIPS ML Systems Workshop, p. 10 (2017)
Das, A., Hossain, M.S., Muhammad Abdullah, S., Ul Islam, R.: Permutation free encoding technique for evolving neural networks. In: Sun, F., Zhang, J., Tan, Y., Cao, J., Yu, W. (eds.) ISNN 2008. LNCS, vol. 5263, pp. 255–265. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-87732-5_29
Deng, L., Li, G., Han, S., Shi, L., Xie, Y.: Model compression and hardware acceleration for neural networks: a comprehensive survey. Proc. IEEE 108(4), 485–532 (2020). https://doi.org/10.1109/JPROC.2020.2976475
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long and Short Papers), pp. 4171–4186. Association for Computational Linguistics, Minneapolis, Minnesota, June 2019. https://doi.org/10.18653/v1/N19-1423, https://www.aclweb.org/anthology/N19-1423
Dürr, P., Mattiussi, C., Floreano, D.: Neuroevolution with analog genetic encoding. In: Runarsson, T.P., Beyer, H.-G., Burke, E., Merelo-Guervós, J.J., Whitley, L.D., Yao, X. (eds.) PPSN 2006. LNCS, vol. 4193, pp. 671–680. Springer, Heidelberg (2006). https://doi.org/10.1007/11844297_68
Edwards, H., Storkey, A.: Towards a neural statistician. In: 5th International Conference on Learning Representations (ICLR 2017), pp. 1–13 (2017)
Eliasmith, C., Anderson, C.H.: Neural Engineering: Computation, Representation, and Dynamics in Neurobiological Systems. Computational Neuroscience Series, A Bradford Book, Cambridge, MA, USA, October 2002
Fukushima, K., Miyake, S.: Neocognitron: a self-organizing neural network model for a mechanism of visual pattern recognition. In: Amari, S., Arbib, M.A. (eds.) Competition and Cooperation in Neural Nets, vol. 45, pp. 267–285. Springer, Berlin (1982). https://doi.org/10.1007/978-3-642-46466-9_18
Gomez, F.J.: Robust Non-Linear Control through Neuroevolution. Ph.D. thesis, University of Texas at Austin, August 2003
Haase, D., Amthor, M.: Rethinking depthwise separable convolutions: how intra-kernel correlations lead to improved mobilenets. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14588–14597. IEEE, Seattle, WA, USA, June 2020. https://doi.org/10.1109/CVPR42600.2020.01461
Hausknecht, M., Khandelwal, P., Miikkulainen, R., Stone, P.: HyperNEAT-GGP: a hyperNEAT-based Atari general game player. In: Proceedings of the 14th Annual Conference on Genetic and Evolutionary Computation, pp. 217–224 (2012)
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), pp. 770–778, June 2016. https://doi.org/10.1109/CVPR.2016.90
Jaderberg, M., Vedaldi, A., Zisserman, A.: Speeding up convolutional neural networks with low rank expansions. In: Proceedings of the British Machine Vision Conference 2014, pp. 88.1–88.13. British Machine Vision Association, Nottingham (2014). https://doi.org/10.5244/C.28.88
Karaletsos, T., Dayan, P., Ghahramani, Z.: Probabilistic meta-representations of neural networks. arXiv:1810.00555, October 2018
Kiers, H.: Towards a standardized notation and terminology in multiway analysis. J. Chemometrics 14, 105–122 (2000). https://doi.org/10.1002/1099-128X(200005/06)14:33.0.CO;2-I
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)
Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM Rev. 51(3), 455–500 (2009). https://doi.org/10.1137/07070111X
Koutník, J., Cuccu, G., Schmidhuber, J., Gomez, F.: Evolving large-scale neural networks for vision-based reinforcement learning. In: Proceedings of the 15th Annual Conference on Genetic and Evolutionary Computation, pp. 1061–1068 (2013)
Krizhevsky, A.: Learning Multiple Layers of Features from Tiny Images. Technical Report TR-2009 (2009)
LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)
LeCun, Y., Cortes, C., Burges, C.: MNIST handwritten digit database. ATT Labs. 7, 6 (2010). http://yann.lecun.com/exdb/mnist
Lee, J., Lee, Y., Kim, J., Kosiorek, A., Choi, S., Teh, Y.W.: Set transformer: a framework for attention-based permutation-invariant neural networks. In: International Conference on Machine Learning, pp. 3744–3753. PMLR, May 2019
Moriarty, D.E., Mikkulainen, R.: Efficient reinforcement learning through symbiotic evolution. Mach. Learn. 22(1), 11–32 (1996). https://doi.org/10.1023/A:1018004120707
Oseledets, I.: Tensor-train decomposition. SIAM J. Sci. Comput. 33, 2295–2317 (2011). https://doi.org/10.1137/090752286
Page, D.: How to Train Your ResNet, September 2018
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)
Reisinger, J., Miikkulainen, R.: Acquiring evolvability through adaptive representations. In: Proceedings of the 9th Annual Conference on Genetic and Evolutionary Computation - GECCO 2007, p. 1045. ACM Press, London, England (2007). https://doi.org/10.1145/1276958.1277164
Schmidhuber, J.: Discovering neural nets with low Kolmogorov complexity and high generalization capability. Neural Netw. 10(5), 857–873 (1997)
Schmidhuber, J., Wierstra, D., Gagliolo, M., Gomez, F.: Training recurrent networks by Evolino. Neural Comput. 19(3), 757–779 (2007). https://doi.org/10.1162/neco.2007.19.3.757
Smith, L.N.: A disciplined approach to neural network hyper-parameters: part 1-learning rate, batch size, momentum, and weight decay. arXiv preprint arXiv:1803.09820 (2018)
Smith, L.N., Topin, N.: Super-convergence: very fast training of neural networks using large learning rates. In: Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, vol. 11006, p. 1100612. International Society for Optics and Photonics (2019)
Stanley, K.O., Clune, J., Lehman, J., Miikkulainen, R.: Designing neural networks through neuroevolution. Nat. Mach. Intell. 1(1), 24–35 (2019)
Stanley, K.O., D’Ambrosio, D.B., Gauci, J.: A hypercube-based encoding for evolving large-scale neural networks. Artif. Life 15(2), 185–212 (2009)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)
Stanley, K.O., Miikkulainen, R.: A taxonomy for artificial embryogeny. Artif. Life 9(2), 93–130 (2003)
Tang, Y., Ha, D.: The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning. arXiv:2109.02869, September 2021
Tang, Y., Nguyen, D., Ha, D.: Neuroevolution of self-interpretable agents. In: Proceedings of the 2020 Genetic and Evolutionary Computation Conference, pp. 414–424 (2020)
Tucker, L.R.: Some mathematical notes on three-mode factor analysis. Psychometrika 31(3), 279–311 (1966). https://doi.org/10.1007/BF02289464
Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, pp. 6000–6010. Curran Associates Inc., Red Hook, NY, USA, December 2017
Wang, Z., Liu, J.C.: Translating math formula images to latex sequences using deep neural networks with sequence-level training (2019)
Yu, X., Liu, T., Wang, X., Tao, D.: On compressing deep models by low rank and sparse decomposition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 67–76. IEEE, Honolulu, HI, July 2017. https://doi.org/10.1109/CVPR.2017.15
Zaheer, M., Kottur, S., Ravanbakhsh, S., Poczos, B., Salakhutdinov, R.R., Smola, A.J.: Deep sets. In: Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, R., Muise, C., Hu, T. (2022). Permutation-Invariant Representation of Neural Networks with Neuron Embeddings. In: Medvet, E., Pappa, G., Xue, B. (eds) Genetic Programming. EuroGP 2022. Lecture Notes in Computer Science, vol 13223. Springer, Cham. https://doi.org/10.1007/978-3-031-02056-8_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-02056-8_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-02055-1
Online ISBN: 978-3-031-02056-8
eBook Packages: Computer ScienceComputer Science (R0)