ABSTRACT
Cancer is a complex disease, the understanding and treatment of which are being aided through increases in the volume of collected data and in the scale of deployed computing power. Consequently, there is a growing need for the development of data-driven and, in particular, deep learning methods for various tasks such as cancer diagnosis, detection, prognosis, and prediction. Despite recent successes, however, designing high-performing deep learning models for nonimage and nontext cancer data is a time-consuming, trial-and-error, manual task that requires both cancer domain and deep learning expertise. To that end, we develop a reinforcement-learning-based neural architecture search to automate deep-learning-based predictive model development for a class of representative cancer data. We develop custom building blocks that allow domain experts to incorporate the cancer-data-specific characteristics. We show that our approach discovers deep neural network architectures that have significantly fewer trainable parameters, shorter training time, and accuracy similar to or higher than those of manually designed architectures. We study and demonstrate the scalability of our approach on up to 1,024 Intel Knights Landing nodes of the Theta supercomputer at the Argonne Leadership Computing Facility.
- [n. d.]. AutoML Workshops. https://www.ml4aad.org/automl/Google Scholar
- [n. d.]. CANDLE Exascale Computing Program Application. https://github.com/ECP-CANDLE/BenchmarksGoogle Scholar
- [n. d.]. Combo Benchmark. https://github.com/ECP-CANDLE/Benchmarks/tree/master/Pilot1/ComboGoogle Scholar
- [n. d.]. An End-to-End AutoML Solution for Tabular Data at KaggleDays. https://ai.googleblog.com/2019/05/an-end-to-end-automl-solution-for.htmlGoogle Scholar
- [n. d.]. Exascale Deep Learning and Simulation Enabled Precision Medicine for Cancer. https://candle.cels.anl.govGoogle Scholar
- [n. d.]. Literature on Neural Architecture Search. https://www.ml4aad.org/automl/literature-on-neural-architecture-search/Google Scholar
- [n. d.]. Neural Network Intelligence. https://github.com/Microsoft/nniGoogle Scholar
- [n. d.]. NT3 Benchmark. https://github.com/ECP-CANDLE/Benchmarks/tree/master/Pilot1/NT3Google Scholar
- [n. d.]. Uno Benchmark. https://github.com/ECP-CANDLE/Benchmarks/tree/master/Pilot1/UnoGoogle Scholar
- [n. d.]. World Health Organization: Cancer key facts. https://www.who.int/news-room/fact-sheets/detail/cancerGoogle Scholar
- Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. TensorFlow: A system for large-scale machine learning. In OSDI, Vol. 16. 265--283.Google ScholarDigital Library
- Anubhav Ashok, Nicholas Rhinehart, Fares Beainy, and Kris M Kitani. 2017. N2n learning: Network to network compression via policy gradient reinforcement learning. arXiv preprint 1709.06030 (2017).Google Scholar
- Bowen Baker, Otkrist Gupta, Nikhil Naik, and Ramesh Raskar. 2016. Designing neural network architectures using reinforcement learning. arXiv preprint 1611.02167 (2016).Google Scholar
- P. Balaprakash, R. Egele, M. Salim, V. Vishwanath, and S. M. Wild. 2018. Deep-Hyper: Scalable automated machine learning package. https://github.com/deephyper/deephyperGoogle Scholar
- Prasanna Balaprakash, Michael Salim, Thomas Uram, Venkat Vishwanath, and Stefan Wild. 2018. DeepHyper: Asynchronous Hyperparameter Search for Deep Neural Networks. In HiPC 2018: 25th edition of the IEEE International Conference on High Performance Computing, Data, and Analytics.Google Scholar
- Irwan Bello, Barret Zoph, Vijay Vasudevan, and Quoc V Le. 2017. Neural optimizer search with reinforcement learning. In Proceedings of the 34th International Conference on Machine Learning, Vol. 70. JMLR. org, 459--468.Google Scholar
- T. Ben-Nun and T. Hoefler. 2018. Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis. CoRR abs/1802.09941 (Feb. 2018).Google Scholar
- Gabriel Bender, Pieter-Jan Kindermans, Barret Zoph, Vijay Vasudevan, and Quoc Le. 2018. Understanding and simplifying one-shot architecture search. In International Conference on Machine Learning. 549--558.Google Scholar
- Gabriel Bender, Pieter-Jan Kindermans, Barret Zoph, Vijay Vasudevan, and Quoc Le. 2018. Understanding and Simplifying One-Shot Architecture Search. In Proceedings of the 35th International Conference on Machine Learning (Proceedings of Machine Learning Research), Jennifer Dy and Andreas Krause (Eds.), Vol. 80. PMLR, 550--559.Google Scholar
- James Bergstra and Yoshua Bengio. 2012. Random search for hyper-parameter optimization. Journal of Machine Learning Research 13, Feb (2012), 281--305.Google ScholarDigital Library
- James Bergstra, Dan Yamins, and David D Cox. 2013. Hyperopt: A Python library for optimizing the hyperparameters of machine learning algorithms. In Proceedings of the 12th Python in Science Conference. 13--20.Google ScholarCross Ref
- James Bergstra, Daniel Yamins, and David Daniel Cox. 2013. Making a science of model search: Hperparameter optimization in hundreds of dimensions for vision architectures. (2013).Google Scholar
- Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. 2016. OpenAI Gym. arXiv:arXiv:1606.01540Google Scholar
- Michael M Bronstein, Joan Bruna, Yann LeCun, Arthur Szlam, and Pierre Vandergheynst. 2017. Geometric deep learning: Going beyond euclidean data. IEEE Signal Processing Magazine 34, 4 (2017), 18--42.Google ScholarCross Ref
- Yukang Chen, Qian Zhang, Chang Huang, Lisen Mu, Gaofeng Meng, and Xinggang Wang. 2018. Reinforced Evolutionary Neural Architecture Search. arXiv preprint 1808.00193 (2018).Google Scholar
- François Chollet et al. 2017. Keras (2015).Google Scholar
- Patryk Chrabaszcz, Ilya Loshchilov, and Frank Hutter. 2017. A downsampled variant of ImageNet as an alternative to the CIFAR datasets. arXiv preprint 1707.08819 (2017).Google Scholar
- Xiangxiang Chu, Bo Zhang, Hailong Ma, Ruijun Xu, Jixiang Li, and Qingyuan Li. 2019. Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search. arXiv preprint 1901.07261 (2019).Google Scholar
- Prafulla Dhariwal, Christopher Hesse, Oleg Klimov, Alex Nichol, Matthias Plappert, Alec Radford, John Schulman, Szymon Sidor, Yuhuai Wu, and Peter Zhokhov. 2017. OpenAI baselines. https://github.com/openai/baselines.Google Scholar
- Georgi Dikov, Patrick van der Smagt, and Justin Bayer. 2019. Bayesian Learning of Neural Network Architectures. arXiv preprint 1901.04436 (2019).Google Scholar
- Jesse R Dixon, Jie Xu, Vishnu Dileep, Ye Zhan, Fan Song, Victoria T Le, Galip Gürkan Yardimci, Abhijit Chakraborty, Darrin V Bann, Yanli Wang, et al. 2018. Integrative detection and analysis of structural variation in cancer genomes. Nature Genetics 50, 10 (2018), 1388.Google ScholarCross Ref
- Thomas Elsken, Jan Hendrik Metzen, and Frank Hutter. 2018. Neural architecture search: A survey. arXiv preprint 1808.05377 (2018).Google Scholar
- Manuel Fernández-Delgado, Eva Cernadas, Senén Barro, and Dinani Amorim. 2014. Do we need hundreds of classifiers to solve real world classification problems? The Journal of Machine Learning Research 15, 1 (2014), 3133--3181.Google ScholarDigital Library
- Dario Floreano, Peter Dürr, and Claudio Mattiussi. 2008. Neuroevolution: From architectures to learning. Evolutionary Intelligence 1, 1 (2008), 47--62.Google ScholarCross Ref
- Ivo Grondman, Lucian Busoniu, Gabriel AD Lopes, and Robert Babuska. 2012. A survey of actor-critic reinforcement learning: SStandard and natural policy gradients. IEEE Transactions on Systems, Man, and Cybernetics, Part C(Applications and Reviews) 42, 6 (2012), 1291--1307.Google ScholarDigital Library
- Minghao Guo, Zhao Zhong, Wei Wu, Dahua Lin, and Junjie Yan. 2018. IRLAS: Inverse Reinforcement Learning for Architecture Search. arXiv preprint 1812.05285 (2018).Google Scholar
- F. Hutter, L. Kotthoff, and J. Vanschoren (Eds.). 2019. Automated Machine Learning: Methods, Systems, Challenges. Springer International Publishing.Google Scholar
- Max Jaderberg, Valentin Dalibard, Simon Osindero, Wojciech M Czarnecki, Jeff Donahue, Ali Razavi, Oriol Vinyals, Tim Green, Iain Dunning, Karen Simonyan, et al. 2017. Population Based Training of Neural Networks. arXiv preprint 1711.09846 (2017).Google Scholar
- Haifeng Jin, Qingquan Song, and Xia Hu. 2018. Efficient neural architecture search with network morphism. arXiv preprint 1806.10282 (2018).Google Scholar
- Purushotham Kamath, Abhishek Singh, and Debo Dutta. [n. d.]. AMLA: An AutoML frAmework for Neural Network Design. ([n. d.]).Google Scholar
- Kirthevasan Kandasamy, Willie Neiswanger, Jeff Schneider, Barnabas Poczos, and Eric P Xing. 2018. Neural architecture search with Bayesian optimisation and optimal transport. In Advances in Neural Information Processing Systems. 2020--2029.Google Scholar
- A. Klein, S. Falkner, N. Mansur, and F. Hutter. 2017. RoBO: A flexible and robust Bayesian Optimization framework in Python. In NeurIPS 2017 Bayesian Optimization Workshop.Google Scholar
- Aaron Klein, Stefan Falkner, Jost Tobias Springenberg, and Frank Hutter. 2016. Learning curve prediction with Bayesian neural networks. (2016).Google Scholar
- Lisha Li, Kevin Jamieson, Giulia DeSalvo, Afshin Rostamizadeh, and Ameet Talwalkar. 2016. Hyperband: Bandit-based configuration evaluation for hyperparameter optimization. (2016).Google Scholar
- Liam Li and Ameet Talwalkar. 2019. Random Search and Reproducibility for Neural Architecture Search. arXiv preprint 1902.07638 (2019).Google Scholar
- Jason Liang, Elliot Meyerson, Babak Hodjat, Dan Fink, Karl Mutch, and Risto Miikkulainen. 2019. Evolutionary Neural AutoML for Deep Learning. arXiv preprint 1902.06827 (2019).Google Scholar
- Jason Liang, Elliot Meyerson, and Risto Miikkulainen. 2018. Evolutionary architecture search for deep multitask networks. In Proceedings of the Genetic and Evolutionary Computation Conference. ACM, 466--473.Google ScholarDigital Library
- Shaoping Ling, Zheng Hu, Zuyu Yang, Fang Yang, Yawei Li, Pei Lin, Ke Chen, Lili Dong, Lihua Cao, Yong Tao, et al. 2015. Extremely high genetic diversity in a single tumor points to prevalence of non-Darwinian cell evolution. Proceedings of the National Academy of Sciences 112, 47 (2015), E6496--E6505.Google ScholarCross Ref
- Chenxi Liu, Barret Zoph, Jonathon Shlens, Wei Hua, Li-Jia Li, Li Fei-Fei, Alan Yuille, Jonathan Huang, and Kevin Murphy. 2017. Progressive neural architecture search. arXiv preprint 1712.00559 (2017).Google Scholar
- Pablo Ribalta Lorenzo and Jakub Nalepa. 2018. Memetic evolution of deep neural networks. In Proceedings of the Genetic and Evolutionary Computation Conference. ACM, 505--512.Google ScholarDigital Library
- Pablo Ribalta Lorenzo, Jakub Nalepa, Luciano Sanchez Ramos, and José Ranilla Pastor. 2017. Hyper-parameter selection in deep neural networks using parallel particle swarm optimization. In Proceedings of the Genetic and Evolutionary Computation Conference Companion. ACM, 1864--1871.Google ScholarDigital Library
- Minh-Thang Luong, Hieu Pham, and Christopher D Manning. 2015. Effective approaches to attention-based neural machine translation. arXiv preprint 1508.04025 (2015).Google Scholar
- Krzysztof Maziarz, Andrey Khorlin, Quentin de Laroussilhe, and Andrea Gesmundo. 2018. Evolutionary-Neural Hybrid Agents for Architecture Search. arXiv preprint 1811.09828 (2018).Google Scholar
- Risto Miikkulainen, Jason Liang, Elliot Meyerson, Aditya Rawal, Dan Fink, Olivier Francon, Bala Raju, Arshak Navruzyan, Nigel Duffy, and Babak Hodjat. 2017. Evolving deep neural networks. arXiv preprint 1703.00548 (2017).Google Scholar
- Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I Jordan, et al. 2018. Ray: A Distributed Framework for Emerging {AI} Applications. In 13th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 18). 561--577.Google ScholarDigital Library
- Renato Negrinho and Geoff Gordon. 2017. Deeparchitect: Automatically designing and training deep architectures. arXiv preprint 1704.08792 (2017).Google Scholar
- Michail Nikolaou, Athanasia Pavlopoulou, Alexandros G Georgakilas, and Efthymios Kyrodimos. 2018. The challenge of drug resistance in cancer treatment: A current overview. Clinical & Experimental Metastasis 35, 4 (2018), 309--318.Google ScholarCross Ref
- Randal S. Olson, Nathan Bartley, Ryan J. Urbanowicz, and Jason H. Moore. 2016. Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science. In Proceedings of the Genetic and Evolutionary Computation Conference 2016 (GECCO '16). ACM, New York, NY, USA, 485--492. Google ScholarDigital Library
- Robert M Patton, J Travis Johnston, Steven R Young, Catherine D Schuman, Don D March, Thomas E Potok, Derek C Rose, Seung-Hwan Lim, Thomas P Karnowski, Maxim A Ziatdinov, et al. 2018. 167-PFlops deep learning for electron microscopy: From learning physics to atomic manipulation. In Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis. IEEE Press, 50.Google ScholarDigital Library
- F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 12 (2011), 2825--2830.Google ScholarDigital Library
- Hieu Pham, Melody Y Guan, Barret Zoph, Quoc V Le, and Jeff Dean. 2018. Efficient Neural Architecture Search via Parameter Sharing. arXiv preprint 1802.03268 (2018).Google Scholar
- Aditya Rawal and Risto Miikkulainen. 2018. From nodes to networks: Evolving recurrent neural networks. arXiv preprint 1803.04439 (2018).Google Scholar
- Esteban Real, Alok Aggarwal, Yanping Huang, and Quoc V Le. 2018. Regularized evolution for image classifier architecture search. arXiv preprint 1802.01548 (2018).Google Scholar
- Ed Reznik, Augustin Luna, Bülent Arman Aksoy, Eric Minwei Liu, Konnor La, Irina Ostrovnaya, Chad J Creighton, A Ari Hakimi, and Chris Sander. 2018. A landscape of metabolic variation across tumor types. Cell Systems 6, 3 (2018), 301--313.Google ScholarCross Ref
- Raanan Y Rohekar, Shami Nisimov, Yaniv Gurwicz, Guy Koren, and Gal Novik. 2018. Constructing Deep Neural Networks by Bayesian Network Structure Learning. In Advances in Neural Information Processing Systems. 3051--3062.Google Scholar
- Michael A. Salim, Thomas D. Uram, Taylor Childers, Prasanna Balaprakash, Venkatram Vishwanath, and Michael E. Papka. 2018. Balsam: Automated Scheduling and Execution of Dynamic, Data-Intensive Workflows. In PyHPC 2018: Proceedings of the 8th Workshop on Python for High-Performance and Scientific Computing.Google Scholar
- Francisco Sanchez-Vega, Marco Mina, Joshua Armenia, Walid K Chatila, Augustin Luna, Konnor C La, Sofia Dimitriadoy, David L Liu, Havish S Kantheti, Sadegh Saghafinia, et al. 2018. Oncogenic signaling pathways in the cancer genome atlas. Cell 173, 2 (2018), 321--337.Google ScholarCross Ref
- John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017).Google Scholar
- Christian Sciuto, Kaicheng Yu, Martin Jaggi, Claudiu Musat, and Mathieu Salzmann. 2019. Evaluating the Search Phase of Neural Architecture Search. arXiv preprint 1902.08142 (2019).Google Scholar
- Jasper Snoek, Hugo Larochelle, and Ryan P Adams. 2012. Practical Bayesian optimization of machine learning algorithms. In Advances in Neural Information Processing Systems. 2951--2959.Google Scholar
- Jasper Snoek, Oren Rippel, Kevin Swersky, Ryan Kiros, Nadathur Satish, Narayanan Sundaram, Mostofa Patwary, Mr Prabhat, and Ryan Adams. 2015. Scalable Bayesian optimization using deep neural networks. In International Conference on Machine Learning. 2171--2180.Google Scholar
- Kenneth O. Stanley, Jeff Clune, Joel Lehman, and Risto Miikkulainen. 2019. Designing neural networks through neuroevolution. Nature Machine Intelligence 1, 1 (2019), 24--35. Google ScholarCross Ref
- Kenneth O Stanley, David B D'Ambrosio, and Jason Gauci. 2009. A hypercube-based encoding for evolving large-scale neural networks. Artificial Life 15, 2 (2009), 185--212.Google ScholarDigital Library
- Masanori Suganuma, Mete Ozay, and Takayuki Okatani. 2018. Exploiting the potential of standard convolutional autoencoders for image restoration by evolutionary search. arXiv preprint 1803.00370 (2018).Google Scholar
- Masanori Suganuma, Shinichi Shirakawa, and Tomoharu Nagao. 2017. A genetic programming approach to designing convolutional neural network architectures. In Proceedings of the Genetic and Evolutionary Computation Conference. ACM, 497--504.Google ScholarDigital Library
- Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement learning: An introduction. MIT Press.Google Scholar
- Richard S. Sutton, David A. McAllester, Satinder P. Singh, and Yishay Mansour. 2000. Policy gradient methods for reinforcement learning with function approximation. In Advances in neural information processing systems. 1057--1063.Google Scholar
- Gerard Jacques van Wykand Anna Sergeevna Bosman. 2018. Evolutionary Neural Architecture Search for Image Restoration. arXiv preprint 1812.05866 (2018).Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008.Google Scholar
- Jiazhuo Wang, Jason Xu, and Xuejun Wang. 2018. Combination of hyperband and Bayesian optimization for hyperparameter optimization in deep learning. arXiv preprint 1801.01596 (2018).Google Scholar
- Daan Wierstra, Faustino J Gomez, and Jürgen Schmidhuber. 2005. Modeling systems with internal state using Evolino. In Proceedings of the 7th Annual Conference on Genetic and Evolutionary Computation. ACM, 1795--1802.Google ScholarDigital Library
- Martin Wistuba. 2017. Bayesian Optimization Combined with Incremental Evaluation for Neural Network Architecture Optimization. Proceedings of the International Workshop on Automatic Selection, Configuration and Composition of Machine Learning Algorithms (2017).Google Scholar
- Justin M. Wozniak, Rajeev Jain, Prasanna Balaprakash, Jonathan Ozik, Nicholson T. Collier, John Bauer, Fangfang Xia, Thomas S. Brettin, Rick Stevens, Jamaludin Mohd-Yusof, Cristina Garcia-Cardona, Brian Van Essen, and Matthew Baughman. 2018. CANDLE/Supervisor: A workflow framework for machine learning applied to cancer research. BMC Bioinformatics 19-S, 18 (2018), 59--69. Google ScholarCross Ref
- Fangfang Xia, Maulik Shukla, Thomas Brettin, Cristina Garcia-Cardona, Judith Cohn, Jonathan E Allen, Sergei Maslov, Susan L Holbeck, James H Doroshow, Yvonne A Evrard, et al. 2018. Predicting tumor cell line response to drug pairs with deep learning. BMC Bioinformatics 19, 18 (2018), 486.Google ScholarCross Ref
- Sirui Xie, Hehui Zheng, Chunxiao Liu, and Liang Lin. 2018. SNAS: Stochastic neural architecture search. arXiv preprint 1812.09926 (2018).Google Scholar
- Steven R Young, Derek C Rose, Travis Johnston, William T Heller, Thomas P Karnowski, Thomas E Potok, Robert M Patton, Gabriel Perdue, and Jonathan Miller. 2017. Evolving deep networks using HPC. In Proceedings of the Machine Learning on HPC Environments. ACM.Google ScholarDigital Library
- Arber Zela, Aaron Klein, Stefan Falkner, and Frank Hutter. 2018. Towards automated deep learning: Efficient joint neural architecture and hyperparameter search. arXiv preprint 1807.06906 (2018).Google Scholar
- Barret Zoph and Quoc V Le. 2016. Neural architecture search with reinforcement learning. arXiv preprint 1611.01578 (2016).Google Scholar
- Barret Zoph, Vijay Vasudevan, Jonathon Shlens, and Quoc V Le. 2018. Learning transferable architectures for scalable image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8697--8710.Google ScholarCross Ref
Index Terms
- Scalable reinforcement-learning-based neural architecture search for cancer deep learning research
Recommendations
Breast cancer masses classification using deep convolutional neural networks and transfer learning
AbstractWith the recent advances in the deep learning field, the use of deep convolutional neural networks (DCNNs) in biomedical image processing becomes very encouraging. This paper presents a new classification model for breast cancer masses based on ...
Deep learning in neural networks
In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. ...
Robust Deep Reinforcement Learning with Adversarial Attacks
AAMAS '18: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent SystemsThis paper proposes adversarial attacks for Reinforcement Learning (RL). These attacks are then leveraged during training to improve the robustness of RL within robust control framework. We show that this adversarial training of DRL algorithms like Deep ...
Comments