Saved in:
Bibliographic Details
Main Authors: Li, Mengqi, Lin, Wensheng, Yang, Jinshuai, Li, Lixin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.08833
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911667053395968
author Li, Mengqi
Lin, Wensheng
Yang, Jinshuai
Li, Lixin
author_facet Li, Mengqi
Lin, Wensheng
Yang, Jinshuai
Li, Lixin
contents Effective sequence modeling fundamentally requires balancing the retention of unbounded history with the high-resolution detection of abrupt short-term variations common in real-world phenomena. However, existing state space models (SSMs) relying on high-order polynomial projection operators (HiPPO) face a critical trade-off where uniform measures dilute recent information to maintain timescale invariance, while exponential measures sacrifice global context to capture local dynamics. This paper proposes a Fractional Recurrent Architecture for Computational Temporal Analysis of Long sequences (FRACTAL), a novel architecture integrating fractional measure theory into recursive memory updates to address this limitation. By deriving projection operators with analytically characterized spectral properties and a tunable singularity index, the proposed method amplifies sensitivity to recent signal perturbations while preserving the spectral structure that encodes scale-invariant memory dynamics. This theoretical innovation is instantiated within a simplified diagonalized state space framework by modulating input projection initialization to enable simultaneous capture of multi-scale temporal features. FRACTAL achieves an average score of 87.11\% on the Long Range Arena benchmark, including 61.85\% on the ListOps task, outperforming the S5 model.
format Preprint
id arxiv_https___arxiv_org_abs_2605_08833
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FRACTAL: SSM with Fractional Recurrent Architecture for Computational Temporal Analysis of Long Sequences
Li, Mengqi
Lin, Wensheng
Yang, Jinshuai
Li, Lixin
Artificial Intelligence
Effective sequence modeling fundamentally requires balancing the retention of unbounded history with the high-resolution detection of abrupt short-term variations common in real-world phenomena. However, existing state space models (SSMs) relying on high-order polynomial projection operators (HiPPO) face a critical trade-off where uniform measures dilute recent information to maintain timescale invariance, while exponential measures sacrifice global context to capture local dynamics. This paper proposes a Fractional Recurrent Architecture for Computational Temporal Analysis of Long sequences (FRACTAL), a novel architecture integrating fractional measure theory into recursive memory updates to address this limitation. By deriving projection operators with analytically characterized spectral properties and a tunable singularity index, the proposed method amplifies sensitivity to recent signal perturbations while preserving the spectral structure that encodes scale-invariant memory dynamics. This theoretical innovation is instantiated within a simplified diagonalized state space framework by modulating input projection initialization to enable simultaneous capture of multi-scale temporal features. FRACTAL achieves an average score of 87.11\% on the Long Range Arena benchmark, including 61.85\% on the ListOps task, outperforming the S5 model.
title FRACTAL: SSM with Fractional Recurrent Architecture for Computational Temporal Analysis of Long Sequences
topic Artificial Intelligence
url https://arxiv.org/abs/2605.08833