Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform

Mateusz Wójcik, Witold Kościukiewicz, Mateusz Baran, Tomasz Kajdanowicz, Adam Gonczarek


Abstract
Production deployments in complex systems require ML architectures to be highly efficient and usable against multiple tasks. Particularly demanding are classification problems in which data arrives in a streaming fashion and each class is presented separately. Recent methods with stochastic gradient learning have been shown to struggle in such setups or have limitations like memory buffers, and being restricted to specific domains that disable its usage in real-world scenarios. For this reason, we present a fully differentiable architecture based on the Mixture of Experts model, that enables the training of high-performance classifiers when examples from each class are presented separately. We conducted exhaustive experiments that proved its applicability in various domains and ability to learn online in production environments. The proposed technique achieves SOTA results without a memory buffer and clearly outperforms the reference methods.
Anthology ID:
2023.acl-industry.51
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Sunayana Sitaram, Beata Beigman Klebanov, Jason D Williams
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
527–537
Language:
URL:
https://aclanthology.org/2023.acl-industry.51
DOI:
10.18653/v1/2023.acl-industry.51
Bibkey:
Cite (ACL):
Mateusz Wójcik, Witold Kościukiewicz, Mateusz Baran, Tomasz Kajdanowicz, and Adam Gonczarek. 2023. Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pages 527–537, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform (Wójcik et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-industry.51.pdf