This project tackles the data challenge of enabling efficient neural network architecture search on
the next-generation supercomputers by:
Defining methods
to increase throughput in neural network architecture search, enabling rapid and
flexible training termination
early in the training process across fitness measurements, datasets, and problems
Designing the building blocks
that transform existing neural network architecture search implementations from
tightly-coupled, monolithic
software tools embedding both search and prediction into a flexible, modular, and
reusable workflow in which
search and prediction are decoupled
Generating a searchable and reusable neural network data
commons
that shares full provenance of the lifespan of diverse neural networks through the
generation, training, and validation stages
Developing new curriculum material, online courses, and
online training material
targeting neural network analysis and efficient architecture search topics, and designed
to broader the HPC and AI communities
The project's methods, workflows, and neural network data commons support users in studying a large and
diverse suite of neural
networks and connecting those neural networks with scientific knowledge embedded in real datasets. Users
across scientific domains
can deploy our products to study the fitness curve of neural network, design early termination criteria,
reconstruct neural network
models, and explain and reproduce AI results.
Selected Publications
HSeoyoung An, Georgia Channing, Catherine Schuman, and Michela Taufer
Visual Analytics
Interactive Tool for Neural Network Archaeology.In Proceedings of the IEEE Cluster Conference
(CLUSTER), pages 1–2, Santa Fe, New Mexico, October 2023. IEEE Computer Society.
(2023).
[link]
Nigel Tan, Bogdan Nicolae, Jakob Luettgau, Jack Marquez, Keita Teranishi, Nicolas Morales,
Sanjukta Bhowmick, Michela Taufer, and Franck Cappello
Scalable Checkpointing of Applications with Sparsely Updated Data.In Proceedings of the 52nd International Conference on Parallel Processing (ICPP), pages
1–10, Salt Lake City, UT, USA, August 2023. ACM.
Georgia Channing, Ria Patel, Paula Olaya, Ariel Rorabaugh, Osamu Miyashita, Silvina
Caino-Lores*, Catherine Schuman, Florence Tama, and Michela Taufer.
Composable Workflow for Accelerating Neural Architecture Search Using In Situ Analytics for
Protein Characterization.In Proceedings of the 52nd International Conference on Parallel Processing (ICPP), pages
1–10,
Salt Lake City, UT, USA, August 2023. ACM.
Ariel Keller Rorabaugh, Silvina Caino-Lores, Travis Johnston, and Michela Taufer.
High Frequency Accuracy and Loss Data of Random Neural Networks Trained on Image DatasetsData in Brief, Elsevier, 40:107780,
2022.
[link]
Ariel Keller Rorabaugh, Silvina Caino-Lores, Travis Johnston, and Michela Taufer.
Building High-throughput Neural Architecture Search Workflows via a Decoupled Fitness
Prediction EngineIEEE Trans. Parallel Distributed Syst. (TPDS), 33(11):2913–2926,
2022.
[link]
Paula Olaya, Silvina Caino-Lores, Vanessa Lama, Ria Patel, Ariel Rorabaugh, Osamu Miyashita,
Florence Tama, and Michela Taufer.
Identifying Structural Properties of Proteins from X- ray Free Electron Laser Diffraction
Patterns.In Proceedings of the 18th IEEE International Conference on e-Science (eScience), pages 1–10,
Salt Lake City, Utah, USA, October 2022. IEEE Computer Society.[link]
Ria Patel, Ariel Keller Rorabaugh, Paula Olaya, Silvina Caino-Lores, Georgia Channing, Catherine
Schuman, Osamu Miyashita, Florence Tama, and Michela Taufer.
A Methodology to Generate Efficient Neural Networks for Classification of Scientific
DatasetsIn Proceedings of the 18th IEEE International Conference on e-Science (eScience), pages 1–2,
Salt Lake City, Utah, USA, October 2022. IEEE Computer Society. (Short paper).[link]
Ariel Keller Rorabaugh, Silvina Caino-Lores, Michael R. Wyatt II, Travis Johnston, and Michela
Taufer.
PEng4NN: An Accurate Performance Estimation Engine for Efficient Automated Neural Network
Architecture SearchCoRR, abs/2101.04185,
2021.
[link]
Meet the
Team
Analytics4NN is a
collaborative effort with Systers, an organization for Women in Electrical Engineering and Computer
Science at the University of
Tennessee, Knoxville.
Michela Taufer
PI.
Professor in the Department of Electrical Engineering & Computer Science at
University of Tennessee, Knoxville
Catherine Schuman
Co-PI.
Assistant Professor in the Department of Electrical Engineering & Computer Science at
University of Tennessee, Knoxville
Ariel Rorabaugh
Post-Doctoral Research Associate at University of Tennessee, Knoxville
Paula Olaya
Graduate Research Assistant at University of Tennessee, Knoxville
Georgia Channing
Research Scientist at University of Tennessee, Knoxville
Dr. Kin NG
Postdoctoral Researcher at University of Tennessee, Knoxville
Alumni
Seoyoung (Amy) An
Undergraduate Student at University of Tennessee, Knoxville
Dr. Wissam Sid Lakhdar
Senior Research Scientist at University of Tennessee, Knoxville
Silvina Caino-Lores
Co-PI.
Research Assistant Professor in the Department of Electrical Engineering & Computer
Science at University of Tennessee, Knoxville
Ria Patel
Graduate Research Assistant at University of Tennessee, Knoxville