Sparse Training Theory for Scalable and Efficient Agents

Mocanu, Decebal Constantin; Mocanu, Elena; Pinto, Tiago; Curci, Selima; Nguyen, Phuong; Gibescu, Madeleine; Ernst, Damien; Vale, Zita

Paper published in a book (Scientific congresses and symposiums)

Mocanu, Decebal Constantin; Mocanu, Elena; Pinto, Tiago et al.

2021 • In Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems - Blue Sky Ideas Track

Peer reviewed

Permalink
https://hdl.handle.net/2268/256931

Files (1)Send to Details Statistics Bibliography Similar publications

Files

Full Text

Sparse_Training_Agents_BlueSky_AAMAS2021_CameraReady.pdf

Publisher postprint (586.75 kB)

Download

All documents in ORBi are protected by a user license.

Send to

RIS BibTex APA Chicago Permalink X Linkedin

Details

Keywords :

Intelligent Agents; Autonomous Agents; Sparse Training; Sparse Neural Networks; Scalable Deep Learning; Smart Grid

Abstract :

[en] A fundamental task for artificial intelligence is learning. Deep Neural Networks have proven to cope perfectly with all learnin paradigms, i.e. supervised, unsupervised, and reinforcement learning. Nevertheless, traditional deep learning approaches make use of cloud computing facilities and do not scale well to autonomous agents with low computational resources. Even in the cloud, theysuffer from computational and memory limitations, and they cannot be used to model adequately large physical worlds for agents which assume networks with billions of neurons. These issues are addressed in the last few years by the emerging topic of sparse training, which trains sparse networks from scratch. This paper discusses sparse training state-of-the-art, its challenges and limitations while introducing a couple of new theoretical research directions which has the potential of alleviating sparse training limitations to push deep learning scalability well beyond its current boundaries. Nevertheless, the theoretical advancements impact in complex multi-agents settings is discussed from a real-world perspective, using the smart grid case study.

Disciplines :

Computer science

Author, co-author :

Mocanu, Decebal Constantin

Mocanu, Elena

Pinto, Tiago

Curci, Selima

Nguyen, Phuong

Gibescu, Madeleine

Ernst, Damien ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids

Vale, Zita

Language :

English

Title :

Sparse Training Theory for Scalable and Efficient Agents

Publication date :

May 2021

Event name :

20th International Conference on Autonomous Agents and Multiagent Systems

Event date :

from 03-05-2021 to 07-05-2021

Audience :

International

Main work title :

Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems - Blue Sky Ideas Track

Peer reviewed :

Peer reviewed

Available on ORBi :

since 15 February 2021

Statistics

Number of views

113 (7 by ULiège)

Number of downloads

102 (6 by ULiège)

More statistics

Scopus citations^®

Scopus citations^®
without self-citations

Bibliography

2019. AAMAS 2019 tutorial, Scalable deep learning: from theory to practice. https://sites.google.com/view/scalable-deep-learning.
Kale ab Tessera, Sara Hooker, and Benjamin Rosman. 2021. Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization. arXiv:2102.01670 [cs.LG]
Nir Ailon, Omer Leibovich, and Vineet Nair. 2020. Sparse Linear Networks with a Fixed Butterfly Structure: Theory and Practice. arXiv:2007.08864 [cs.LG]
Zahra Atashgahi, Ghada Sokar, Tim van der Lee, Elena Mocanu, Decebal Constantin Mocanu, Raymond Veldhuis, and Mykola Pechenizkiy. 2020. Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders. arXiv:2012.00560 [cs.LG]
Guillaume Bellec, David Kappel, Wolfgang Maass, and Robert Legenstein. 2018. Deep Rewiring: Training very sparse deep networks. In International Conference on Learning Representations.
Mathijs M. de Weerdt, Michael Albert, Vincent Conitzer, and Koos van der Linden. 2018. Complexity of Scheduling Charging in the Smart Grid. In Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems (Stockholm, Sweden) (AAMAS'18). 3.
Tim Dettmers and Luke Zettlemoyer. 2019. Sparse networks from scratch: Faster training without losing performance. arXiv preprint arXiv:1907.04840 (2019).
S. Dey, K. Huang, P. A. Beerel, and K. M. Chugg. 2019. Pre-Defined Sparse Neural Networks With Hardware Acceleration. IEEE Journal on Emerging and Selected Topics in Circuits and Systems 9, 2 (2019), 332-345.
Virginia Dignum and Frank Dignum. 2020. Agents Are Dead. Long Live Agents! (AAMAS'20). 1701-1705.
Utku Evci, Trevor Gale, Jacob Menick, Pablo Samuel Castro, and Erich Elsen. 2020. Rigging the Lottery: Making All Tickets Winners. In International Conference on Machine Learning.
Utku Evci, Yani A. Ioannou, Cem Keskin, and Yann Dauphin. 2020. Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win. arXiv:2010.03533 [cs.LG]
Jonathan Frankle and Michael Carbin. 2019. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks. In International Conference on Learning Representations.
Daniel Gebbran, Gregor Verbič, Archie C. Chapman, and Sleiman Mhanna. 2020. Coordination of Prosumer Agents via Distributed Optimal Power Flow: An Edge Computing Hardware Prototype. In Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems (Auckland, New Zealand) (AAMAS'20). 2104-2106.
Golnaz Habibi, Zachary Kingston, Zijian Wang, Mac Schwager, and James McLurkin. 2015. Pipelined Consensus for Global State Estimation in Multi-Agent Systems (AAMAS'15). 1315-1323.
Song Han, Jeff Pool, John Tran, and William Dally. 2015. Learning both weights and connections for efficient neural network. In Advances in neural information processing systems. 1135-1143.
Sara Hooker. 2020. The Hardware Lottery. arXiv:2009.06489 [cs.CY]
Siddhant Jayakumar, Razvan Pascanu, Jack Rae, Simon Osindero, and Erich Elsen. 2020. Top-KAST: Top-K Always Sparse Training. In Advances In Neural Information Processing Systems. 1379-1387.
Norman P Jouppi, Cliff Young, Nishant Patil, David Patterson, Gaurav Agrawal, Raminder Bajwa, Sarah Bates, Suresh Bhatia, Nan Boden, Al Borchers, et al. 2017. In-datacenter performance analysis of a tensor processing unit. In Computer Architecture (ISCA), 2017 ACM/IEEE 44th Annual International Symposium on.
Jeremy Kepner, Simon Alford, Vijay Gadepally, Michael Jones, Lauren Milechin, Ryan Robinett, and Sid Samsi. 2019. Sparse Deep Neural Network Graph Challenge. 2019 IEEE High Performance Extreme Computing Conference (HPEC) (2019).
Jeremy Kepner and Ryan Robinett. 2019. Radix-net: Structured sparse matrices for deep neural networks. In 2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, 268-274.
Koen Kok. 2010. Multi-Agent Coordination in the Electricity Grid, from Concept towards Market Introduction (AAMAS'10). 1681-1688.
Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep Learning. Nature 521, 7553 (2015), 436-444.
Yann LeCun, John S Denker, and Sara A Solla. 1990. Optimal brain damage. In Advances in neural information processing systems. 598-605.
Namhoon Lee, Thalaiyasingam Ajanthan, and Philip Torr. 2019. SNIP: single-shot network pruning based on connection sensitivity. In International Conference on Learning Representations.
Junjie Liu, Zhe XU, Runbin SHI, Ray C. C. Cheung, and Hayden K.H. So. 2020. Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers. In International Conference on Learning Representations.
Shiwei Liu, Decebal Constantin Mocanu, Amarsagar Reddy Ramapuram Matavalam, Yulong Pei, and Mykola Pechenizkiy. 2020. Sparse evolutionary deep learning with over one million artificial neurons on commodity hardware. Neural Computing and Applications (2020), 1-16.
Shiwei Liu, Decebal Constantin Mocanu, Yulong Pei, and Mykola Pechenizkiy. 2021. Selfish Sparse RNN Training. arXiv:2101.09048 [cs.LG]
Shiwei Liu, Tim van der Lee, Anil Yaman, Zahra Atashgahi, Davide Ferraro, Ghada Sokar, Mykola Pechenizkiy, and Decebal Constantin Mocanu. 2020. Topological Insights into Sparse Neural Networks. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases.
Christos Louizos, Max Welling, and Diederik P Kingma. 2018. Learning Sparse Neural Networks through L_0 Regularization. In International Conference on Learning Representations.
Decebal Constantin Mocanu. 2017. Network computations in artificial intelligence. Ph.D. Dissertation. Eindhoven University of Technology. https://pure.tue.nl/ws/portalfiles/portal/69949254
Decebal Constantin Mocanu, Elena Mocanu, Phuong H. Nguyen, Madeleine Gibescu, and Antonio Liotta. 2016. A topological insight into restricted Boltzmann machines. Machine Learning 104, 2 (01 Sep 2016), 243-270.
Decebal Constantin Mocanu, Elena Mocanu, Peter Stone, Phuong H Nguyen, Madeleine Gibescu, and Antonio Liotta. 2018. Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nature Communications 9, 1 (2018), 2383.
E. Mocanu, D. C. Mocanu, P. H. Nguyen, A. Liotta, M. E. Webber, M. Gibescu, and J. G. Slootweg. 2019. On-Line Building Energy Optimization Using Deep Reinforcement Learning. IEEE Transactions on Smart Grid 10, 4 (2019), 3698-3708.
Yousuf Ahmad Mohammad Hasanzadeh Mofrad, Rami Melhem and Mohammad Hammoud. 2021. Accelerating Distributed Inference of Sparse Deep Neural Networks via Mitigating the Straggler Effect. In In proceedings of IEEE High Performance Extreme Computing (HPEC), Waltham, MA USA. under review.
Hesham Mostafa and Xin Wang. 2019. Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization. In International Conference on Machine Learning.
Michael C. Mozer and Paul Smolensky. 1989. Using Relevance to Reduce Network Size Automatically. Connection Science 1, 1 (1989), 3-16.
Joshua C. Peterson, David Bourgin, Daniel Reichman, Thomas L. Griffiths, and Stuart J. Russell. 2019. Cognitive model priors for predicting human decisions. In Proceedings of the 36th International Conference on Machine Learning.
Tiago Pinto, Luis Gomes, Pedro Faria, Filipe Sousa, and Zita Vale. 2020. MARTINE: Multi-Agent Based Real-Time INfrastructure for Energy. In Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems (Auckland, New Zealand) (AAMAS'20). 2114-2116.
Ameya Prabhu, Girish Varma, and Anoop Namboodiri. 2018. Deep expander networks: Efficient deep networks from graph theory. In Proceedings of the European Conference on Computer Vision (ECCV). 20-35.
Gobinda Saha and Kaushik Roy. 2021. Gradient Projection Memory for Continual Learning. In International Conference on Learning Representations.
Ghada Sokar, Decebal Constantin Mocanu, and Mykola Pechenizkiy. 2020. SpaceNet: Make Free Space For Continual Learning. arXiv:2007.07617 [cs.LG]
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, Vol. 30.
Chaoqi Wang, Guodong Zhang, and Roger Grosse. 2020. Picking Winning Tickets Before Training by Preserving Gradient Flow. In International Conference on Learning Representations.
Mitchell Wortsman, Vivek Ramanujan, Rosanne Liu, Aniruddha Kembhavi, Mohammad Rastegari, Jason Yosinski, and Ali Farhadi. 2020. Supermasks in Superposition. arXiv:2006.14769 [cs.LG]
Vahid Yazdanpanah, Sara Mehryar, Nicholas R. Jennings, Swenja Surminski, Martin J. Siegert, and Jos van Hillegersberg. 2020. Multiagent Climate Change Research. In Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems (Auckland, New Zealand) (AAMAS'20). 1726-1731.
X. Zeng, T. Zhi, X. Zhou, Z. Du, Q. Guo, S. Liu, B. Wang, Y. Wen, C. Wang, X. Zhou, L. Li, T. Chen, N. Sun, and Y. Chen. 2020. Addressing Irregularity in Sparse Neural Networks Through a Cooperative Software/Hardware Approach. IEEE Trans. Comput. 69, 7 (2020), 968-985.
S. Zhang, Z. Du, L. Zhang, H. Lan, S. Liu, L. Li, Q. Guo, T. Chen, and Y. Chen. 2016. Cambricon-X: An accelerator for sparse neural networks. In 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO). 1-12.
Shunshi Zhang and Bradly C. Stadie. 2020. One-Shot Pruning of Recurrent Neural Networks by Jacobian Spectrum Evaluation. In International Conference on Learning Representations.
Z. Zhang, D. Zhang, and R. C. Qiu. 2020. Deep reinforcement learning for power system applications: An overview. CSEE Journal of Power and Energy Systems 6, 1 (2020), 213-225.
Aojun Zhou, Yukun Ma, Junnan Zhu, Jianbo Liu, Zhijie Zhang, Kun Yuan, Wenxiu Sun, and Hongsheng Li. 2021. Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch. In International Conference on Learning Representations.
H. Zhu and Y. Jin. 2020. Multi-Objective Evolutionary Federated Learning. IEEE Transactions on Neural Networks and Learning Systems 31, 4 (2020), 1310-1322.