Scalable mechanistic neural networks
Chen J, Yao D, Pervez AA, Alistarh D-A, Locatello F. 2025. Scalable mechanistic neural networks. 13th International Conference on Learning Representations. ICLR: International Conference on Learning Representations, 63716–63737.
Download
Conference Paper
| Published
| English
Scopus indexed
Author
Corresponding author has ISTA affiliation
Department
Abstract
We propose Scalable Mechanistic Neural Network (S-MNN), an enhanced neural network framework designed for scientific machine learning applications involving long temporal sequences. By reformulating the original Mechanistic Neural Network (MNN) (Pervez et al., 2024), we reduce the computational time and space complexities from cubic and quadratic with respect to the sequence length, respectively, to linear. This significant improvement enables efficient modeling of long-term dynamics without sacrificing accuracy or interpretability. Extensive experiments demonstrate that S-MNN matches the original MNN in precision while substantially reducing computational resources. Consequently, S-MNN can drop-in replace the original MNN in applications, providing a practical and efficient tool for integrating mechanistic bottlenecks into neural network models of complex dynamical systems. Source code is available at https://github.com/IST-DASLab/ScalableMNN.
Publishing Year
Date Published
2025-04-01
Proceedings Title
13th International Conference on Learning Representations
Publisher
OpenReview
Page
63716-63737
Conference
ICLR: International Conference on Learning Representations
Conference Location
Singapore, Singapore
Conference Date
2025-04-24 – 2025-04-28
ISBN
IST-REx-ID
Cite this
Chen J, Yao D, Pervez AA, Alistarh D-A, Locatello F. Scalable mechanistic neural networks. In: 13th International Conference on Learning Representations. OpenReview; 2025:63716-63737.
Chen, J., Yao, D., Pervez, A. A., Alistarh, D.-A., & Locatello, F. (2025). Scalable mechanistic neural networks. In 13th International Conference on Learning Representations (pp. 63716–63737). Singapore, Singapore: OpenReview.
Chen, Jiale, Dingling Yao, Adeel A Pervez, Dan-Adrian Alistarh, and Francesco Locatello. “Scalable Mechanistic Neural Networks.” In 13th International Conference on Learning Representations, 63716–37. OpenReview, 2025.
J. Chen, D. Yao, A. A. Pervez, D.-A. Alistarh, and F. Locatello, “Scalable mechanistic neural networks,” in 13th International Conference on Learning Representations, Singapore, Singapore, 2025, pp. 63716–63737.
Chen J, Yao D, Pervez AA, Alistarh D-A, Locatello F. 2025. Scalable mechanistic neural networks. 13th International Conference on Learning Representations. ICLR: International Conference on Learning Representations, 63716–63737.
Chen, Jiale, et al. “Scalable Mechanistic Neural Networks.” 13th International Conference on Learning Representations, OpenReview, 2025, pp. 63716–37.
All files available under the following license(s):
Creative Commons Attribution 4.0 International Public License (CC-BY 4.0):
Main File(s)
File Name
2025_ICLR_Chen.pdf
732.75 KB
Access Level

Date Uploaded
2025-07-22
MD5 Checksum
64cfdb12ae3e4e8ba57b1403e1066776
Export
Marked PublicationsOpen Data ISTA Research Explorer
Sources
arXiv 2410.06074