{"publisher":"OpenReview","conference":{"name":"ICLR: International Conference on Learning Representations","end_date":"2025-04-28","location":"Singapore, Singapore","start_date":"2025-04-24"},"external_id":{"arxiv":["2410.06074"]},"language":[{"iso":"eng"}],"has_accepted_license":"1","type":"conference","article_processing_charge":"No","page":"63716-63737","date_created":"2025-07-20T22:02:01Z","year":"2025","status":"public","month":"04","arxiv":1,"_id":"20032","day":"01","quality_controlled":"1","publication_status":"published","author":[{"first_name":"Jiale","full_name":"Chen, Jiale","last_name":"Chen","orcid":"0000-0001-5337-5875","id":"4d0a9064-1ff6-11ee-9fa6-ec046c604785"},{"id":"d3e02e50-48a8-11ee-8f62-c108061797fa","last_name":"Yao","full_name":"Yao, Dingling","first_name":"Dingling"},{"id":"fca6d90c-d47f-11ee-bc87-93ff51604981","first_name":"Adeel A","last_name":"Pervez","full_name":"Pervez, Adeel A"},{"id":"4A899BFC-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0003-3650-940X","last_name":"Alistarh","full_name":"Alistarh, Dan-Adrian","first_name":"Dan-Adrian"},{"orcid":"0000-0002-4850-0683","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","first_name":"Francesco","last_name":"Locatello","full_name":"Locatello, Francesco"}],"department":[{"_id":"DaAl"},{"_id":"FrLo"}],"title":"Scalable mechanistic neural networks","date_updated":"2025-07-22T07:59:26Z","related_material":{"link":[{"relation":"software","url":"https://github.com/IST-DASLab/ScalableMNN"}]},"file_date_updated":"2025-07-22T07:58:22Z","publication":"13th International Conference on Learning Representations","oa":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","abstract":[{"text":"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.","lang":"eng"}],"citation":{"ista":"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.","ama":"Chen J, Yao D, Pervez AA, Alistarh D-A, Locatello F. Scalable mechanistic neural networks. In: <i>13th International Conference on Learning Representations</i>. OpenReview; 2025:63716-63737.","chicago":"Chen, Jiale, Dingling Yao, Adeel A Pervez, Dan-Adrian Alistarh, and Francesco Locatello. “Scalable Mechanistic Neural Networks.” In <i>13th International Conference on Learning Representations</i>, 63716–37. OpenReview, 2025.","mla":"Chen, Jiale, et al. “Scalable Mechanistic Neural Networks.” <i>13th International Conference on Learning Representations</i>, OpenReview, 2025, pp. 63716–37.","apa":"Chen, J., Yao, D., Pervez, A. A., Alistarh, D.-A., &#38; Locatello, F. (2025). Scalable mechanistic neural networks. In <i>13th International Conference on Learning Representations</i> (pp. 63716–63737). Singapore, Singapore: OpenReview.","ieee":"J. Chen, D. Yao, A. A. Pervez, D.-A. Alistarh, and F. Locatello, “Scalable mechanistic neural networks,” in <i>13th International Conference on Learning Representations</i>, Singapore, Singapore, 2025, pp. 63716–63737.","short":"J. Chen, D. Yao, A.A. Pervez, D.-A. Alistarh, F. Locatello, in:, 13th International Conference on Learning Representations, OpenReview, 2025, pp. 63716–63737."},"ddc":["000"],"file":[{"file_name":"2025_ICLR_Chen.pdf","creator":"dernst","checksum":"64cfdb12ae3e4e8ba57b1403e1066776","content_type":"application/pdf","success":1,"file_id":"20065","date_created":"2025-07-22T07:58:22Z","relation":"main_file","access_level":"open_access","date_updated":"2025-07-22T07:58:22Z","file_size":732745}],"oa_version":"Published Version","OA_place":"publisher","scopus_import":"1","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","image":"/images/cc_by.png","short":"CC BY (4.0)"},"date_published":"2025-04-01T00:00:00Z","corr_author":"1","publication_identifier":{"isbn":["9798331320850"]},"OA_type":"diamond"}