Incorporating Exponential Smoothing into MLP: a Simple but Effective Sequence Model

JiqunChu JiqunChu, Zuoquan Lin


Abstract
Modeling long-range dependencies in sequential data is a crucial step in sequence learning. A recently developed model, the Structured State Space (S4), demonstrated significant effectiveness in modeling long-range sequences. However, It is unclear whether the success of S4 can be attributed to its intricate parameterization and HiPPO initialization or simply due to State Space Models (SSMs). To further investigate the potential of the deep SSMs, we start with exponential smoothing (ETS), a simple SSM, and propose a stacked architecture by directly incorporating it into an element-wise MLP. We augment simple ETS with additional parameters and complex field to reduce the inductive bias. Despite increasing less than 1% of parameters of element-wise MLP, our models achieve comparable results to S4 on the LRA benchmark.
Anthology ID:
2024.findings-naacl.23
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
326–337
Language:
URL:
https://aclanthology.org/2024.findings-naacl.23
DOI:
Bibkey:
Cite (ACL):
JiqunChu JiqunChu and Zuoquan Lin. 2024. Incorporating Exponential Smoothing into MLP: a Simple but Effective Sequence Model. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 326–337, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Incorporating Exponential Smoothing into MLP: a Simple but Effective Sequence Model (JiqunChu & Lin, Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.23.pdf
Copyright:
 2024.findings-naacl.23.copyright.pdf